REVIEW 3 major objections 4 minor 295 references
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
T0 review · 3 major / 4 minor · reviewed 2026-08-05 · deepseek-v4-flash
Pith's one-line read For Other-Play, the standard zero-shot-coordination evaluation—inter-seed cross-play from a single implementation—survives variation in implementation details, with no meaningful gap to full cross-implementation cross-play.
desk verdict Useful XIXP evaluation framework and a carefully run null result, but the 'reliable proxy' claim outruns the evidence: unexamined threshold discards half the implementations, and one-at-a-time variation from a single codebase is not independent implementation. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
Cross-implementation cross-play (XIXP): a scheme that turns the standard single-implementation, multi-seed evaluation into a full matrix of implementations. For each pair of distinct implementations it averages cross-play over all seed pairs, and the within-implementation average (WIXP) is the traditional inter-seed cross-play score. The decisive object is the gap WIXP−XIXP; if it stays near zero, implementation details are not creating new coordination failures beyond those already seen across seeds. The paper also uses a paired standard-error estimator, in which each seed contributes exactly one inter-seed pairing per implementation, to keep confidence intervals valid.
What would settle it
Train two or more genuinely independent implementations of Other-Play from the same specification (ideally written by separate teams, then exchanged), apply the same XIXP protocol on Yokai, and see whether the WIXP−XIXP gap stays within the overlapping-confidence-interval range; a large gap would refute the proxy. A cheaper check: add an unvaried detail such as optimizer choice (Adam vs SGD), observation preprocessing, or network width; if the resulting gap is statistically meaningful, inter-seed cross-play is not enough even within the simulated-variation setting.
Extended reading notes
Core claim
The paper's claim is that inter-seed cross-play is a reliable proxy for cross-implementation evaluation in zero-shot coordination. To support this, it defines XIXP as the average cross-play score over all policy pairs drawn from two different implementations, and WIXP as the average within-implementation cross-play score; the gap WIXP−XIXP is the measure of implementation-induced miscoordination. The authors train 22 implementations of Other-Play with IPPO in the Yokai environment, varying λGAE, learning-rate scheduling, gradient and value-function clipping, weight initialization, hidden-layer counts, minibatch counts, discount factor, entropy coefficient, and network architecture. After dis
Load-bearing premise
The load-bearing premise is that the curated list of varied implementation details (λGAE, clipping, initialization, architecture, etc.) faithfully represents the spread of genuinely independent implementations—if independent codebases differ in ways not covered here, the null result may not generalize.
Editorial extensions
If this is right
- ZSC papers can keep using inter-seed cross-play as the primary evaluation without commissioning multiple independent implementations, at least for Other-Play-style algorithms on benchmarks where the competence filter is applied.
- The XIXP protocol—generate implementations, filter by self-play competence, compare WIXP to XIXP—gives future work a concrete template for testing whether a new ZSC algorithm is more or less sensitive to implementation details.
- Nearly half of the generated implementations (11 of 22) failed the self-play competence threshold, so the proxy only holds once implementations are competent; the null result does not license skipping quality control.
- The seed-pairing standard-error estimator shows how a small seed count can distort conclusions; adopting it would make reported confidence intervals in ZSC papers more honest.
- The finding gives an empirical precedent for treating Other-Play as robust to specification ambiguity in the Yokai environment, shifting the burden of proof onto claims that implementation details do break coordination.
Reading between the lines
- Because the paper varies only a curated list of PPO details, the representative-details assumption is a testable extension: compare XIXP against implementations written truly independently from the same specification, and if a gap shows up, the null result is limited to simulated variation.
- If the null result generalizes to other ZSC algorithms, it would suggest that the symmetry-avoiding design principle behind Other-Play also absorbs implementation noise, making algorithmic robustness an emergent property rather than a separate engineering concern.
- The WIXP−XIXP gap could become a standard regression metric in ZSC research—reported alongside seed counts—so that a claimed ZSC algorithm is judged on how much its coordination survives code-level variation, not just seed variation.
- A natural extension is to run the same protocol on Off-Belief Learning and Q-learning variants, since the paper explicitly leaves those open; finding a large gap there would map the boundary of the proxy's validity.
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper asks whether the standard zero-shot coordination (ZSC) evaluation practice — training a single implementation across random seeds and using inter-seed cross-play as a proxy for cross-implementation coordination — is justified. It introduces a new evaluation scheme, cross-implementation cross-play (XIXP), in which implementation variants of the same ZSC algorithm are trained and evaluated against each other. Using Other-Play with IPPO in the Yokai environment, the authors vary nine PPO implementation details (λGAE, learning-rate schedule, gradient/value clipping, initialization, hidden layers, minibatches, discount factor, entropy coefficient, architecture). They train 176 policies across 22 implementations with 8 seeds each, discard 11 implementations whose self-play score is below 5, and report overlapping 95% confidence intervals for WIXP (4.8892, CI 4.6109–5.1675) and XIXP (4.8487, CI 4.7548–4.9427). They conclude that there is no meaningful WIXP−XIXP gap and that inter-seed cross-play is a reliable proxy for cross-implementation evaluation. The paper explicitly limits its scope to one environment, one base algorithm, and one ZSC algorithm, leaving generalization as an open question.
Significance. If the result holds, this is a valuable contribution: it is the first systematic empirical evaluation of a widely used but unexamined evaluation shortcut in ZSC research, and it introduces a reusable XIXP framework. The study is methodologically careful in several respects: it uses 8 seeds per implementation, adopts a CI estimator that avoids the non-independence of all-pairs cross-play, and is attentive to multimodality in cross-play scores. These are real strengths and should be credited. However, the central claim is currently supported only by an informal reading of overlapping confidence intervals and by a filtering step that removes half of the implementations without a sensitivity analysis. The paper is therefore suggestive rather than conclusive, and the breadth of the conclusion in the abstract and Section 6 exceeds what the evidence can bear.
major comments (3)
- [Section 5, Table 1] The central inference — 'no meaningful WIXP−XIXP gap' — is based solely on overlapping 95% confidence intervals. Overlap of two CIs is not evidence of equivalence; it is compatible with a range of true differences, including ones that would undermine the 'reliable proxy' claim. The authors should report a confidence interval for the pairwise difference WIXP−XIXP, or perform a two one-sided tests (TOST) equivalence analysis against a pre-specified and justified bound. Additionally, the CI estimator is only cited to Forkel et al. (2025) and not described; without the estimator formula, the reported intervals are not reproducible from the text.
- [Section 5, SP<5 filter (Figures 4 and 5)] Eleven of the 22 trained implementations are discarded because their self-play score is below 5. This threshold is arbitrary and no sensitivity analysis is provided. As Figure 4 shows, the filter removes all feedforward implementations and several entropy/architecture/PPO variants; these are precisely the implementations that could exhibit a WIXP−XIXP gap if their poor self-play does not translate equally to cross-play. The conclusion is therefore conditional on an unexamined selection step. The authors should justify the threshold from the score distribution, report results for alternative thresholds (e.g., 3, 4, 5, 6), or include all 22 implementations in a supplementary analysis.
- [Sections 4.2 and 6] The implementations used in the study are generated by varying one PPO detail at a time from a single reference codebase. Independent implementations typically differ in combinations of details and in choices not varied here (optimizer details, observation preprocessing, training budgets, replay buffer, etc.). Yet the abstract and Section 6 generalize to 'the standard evaluation practice in ZSC research.' This is a large inferential leap from one environment (Yokai), one base algorithm (IPPO), and one ZSC algorithm (Other-Play). The Section 6 limitations paragraph acknowledges this, but the main claim should be proportionately restricted or supported by additional experiments with combined variations or independently written code.
minor comments (4)
- [Equations (4)-(5) and Figure 2/5 captions] There is an inconsistency: Eq. (4) defines XIXP(L_k,L_k) = XP(L_k), i.e., within-implementation inter-seed cross-play, and WIXP is the average of these diagonal entries. However, the main text says the diagonal tiles in Figure 2 'represent self-play scores for each policy.' Please clarify whether the diagonal in the XIXP matrix shows self-play or within-implementation cross-play; if it is self-play, then WIXP is not computed from the displayed matrix.
- [Section 4.2 and Appendix] The paper does not provide a full hyperparameter table, code release, or environment details needed to reproduce the 22 implementations. Given that the paper's entire argument is about implementation details, a complete list of all varied and fixed hyperparameters (optimizer, learning rate, normalizations, etc.) is essential. Also specify the score range in Yokai and the units of the SP<5 threshold.
- [Section 4.2, CI estimator] The 'estimators proposed by Forkel et al. [2025]' are central to the statistical conclusion but are not defined. Please include the estimator equations or an appendix derivation so the reader can verify the claimed independence properties.
- [Throughout] Minor language and labeling issues: Figure 3/4/5 axis labels are incomplete (e.g., x-axis labeled 'Metric'), and the duplicated implementation names in Figure 5 make it hard to count the 11 retained implementations. Please clean up the figure presentation.
Circularity Check
No significant circularity: the WIXP-vs-XIXP comparison is a direct empirical measurement, not a construction or fitted prediction, and the self-citations are non-load-bearing tools.
full rationale
The paper is an empirical study, not a formal derivation, so the main circularity patterns do not apply. The central quantity WIXP−XIXP is measured directly from trained policies via Equations (4) and (5): WIXP is the average inter-seed cross-play within each implementation, and XIXP is the average cross-play across different implementations. These are operationally distinct objects, and no parameter is fitted to make the gap small; the gap is simply observed to be near zero. The implementation variations (Section 4.2) are grounded in PPO implementation-detail literature (Huang et al., 2022) and are varied one at a time from a single base codebase; this is a limitation on external validity, not a circularity. The competence filter SP<5 (Section 5) discards incompetent policies, which could in principle affect the conclusion, but the retained implementations are still distinct and the comparison is not definitionally forced. The paper explicitly acknowledges its limited scope in Section 6: 'The computational cost of XIXP evaluation restricted our analysis to a single environment (Yokai), a single base algorithm (IPPO), and a single ZSC algorithm (Other-Play).' This honest limitation statement further shows the conclusion is not presented as a tautology. Citations to prior work by the same authors (e.g., Forkel et al. 2025 for standard-error estimators, Ruhdorfer et al. 2026 for the Yokai environment, Hu et al. 2020 for Other-Play) are used as tools or background; the empirical WIXP-vs-XIXP comparison does not reduce to any of these citations. No equation in the paper is equivalent to its input by construction, and the main claim is an empirical finding rather than a derived identity.
Assumptions & free parameters
free parameters (1)
- self-play competence threshold =
5
assumptions (3)
- domain assumption The implementation details varied (lambda-GAE, LR schedule, gradient clipping, value function clipping, weight init, hidden layers, minibatches, discount factor) are the ones that matter for independent implementations of IPPO/Other-Play.
- domain assumption The Yokai environment is a representative ZSC benchmark for evaluating robustness to implementation details.
- domain assumption The seed-pairing estimator from Forkel et al. 2025 preserves independence for valid confidence intervals.
Cite this review
Pith. "Pith review of Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details." pith.science (2026). https://pith.science/paper/XDIEVRFD
@misc{pith2026260803644,
author = {Pith},
title = {Pith review of: Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details},
year = {2026},
howpublished = {\url{https://pith.science/paper/XDIEVRFD}},
note = {Machine review of arXiv:2608.03644}
}
read the original abstract
AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot coordination (ZSC) algorithms aim to achieve this by specifying high-level learning rules such that independently engineered agents can coordinate with each other at test time. Rigorous evaluation of ZSC algorithms remains difficult: ideally, multiple independent implementations of each proposed algorithm must be used, reflecting the variation that arises when independent parties interpret and implement the same specification. In practice, however, ZSC algorithms have almost exclusively been evaluated using a single implementation trained across different random seeds, with only a handful of works additionally varying the neural network architecture. This leaves open questions about robustness to specification ambiguities and implementation details. In this work, we provide the first systematic evaluation of this robustness. We introduce a new evaluation scheme, cross-implementation cross-play, varying implementation details that prior work has shown to affect the performance of multi-agent reinforcement learning (MARL) algorithms, and we evaluate Other-Play, a popular ZSC algorithm, with this scheme. Our findings are encouraging and suggest that, for Other-Play, the standard ZSC evaluation is, in fact, a reasonable proxy for this more thorough cross-implementation evaluation.
Figures
Figures from the paper (2 more)
Reference graph
Works this paper leans on
-
[1]
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
Tessera, Kale-ab Abebe and Szecsenyi, Andras and Barker, Cameron and Rutherford, Alexander and Paglieri, Davide and Scannell, Aidan and Gouk, Henry and Crowley, Elliot J. and Rocktäschel, Tim and Storkey, Amos , month = jun, year =. Benchmarking. doi:10.48550/arXiv.2606.08340 , abstract =
-
[2]
doi:10.48550/arXiv.2603.19312 , abstract =
Maes, Lucas and Lidec, Quentin Le and Scieur, Damien and LeCun, Yann and Balestriero, Randall , month = mar, year =. doi:10.48550/arXiv.2603.19312 , abstract =
-
[3]
Expected
Muglich, Darius and Forkel, Johannes and Pol, Elise van der and Foerster, Jakob Nicolaus , year =. Expected. The
-
[4]
Equivariant networks for zero-shot coordination , isbn =
Muglich, Darius and de Witt, Christian Schroeder and van der Pol, Elise and Whiteson, Shimon and Foerster, Jakob , month = nov, year =. Equivariant networks for zero-shot coordination , isbn =. Proceedings of the 36th
-
[5]
Cui, Brandon and Hu, Hengyuan and Pineda, Luis and Foerster, Jakob , editor =. K-level. Advances in. 2021 , pages =
2021
-
[6]
, month = nov, year =
Cui, Brandon and Hu, Hengyuan and Lupu, Andrei and Sokota, Samuel and Foerster, Jakob N. , month = nov, year =. Off-team learning , isbn =. Proceedings of the 36th
-
[7]
Dizdarević, Tin and Hammond, Ravi and Gessler, Tobias and Calinescu, Anisoara and Cook, Jonathan and Gallici, Matteo and Lupu, Andrei and Foerster, Jakob Nicolaus , editor =. Ad-. Proceedings of the 42nd. 2025 , pages =
2025
-
[8]
How foundation models will revolutionize robot swarms , volume =
Strobel, Volker and Dorigo, Marco and Fritz, Mario , month = apr, year =. How foundation models will revolutionize robot swarms , volume =. Science Robotics , publisher =. doi:10.1126/scirobotics.adz1543 , abstract =
Show all 295 references
- [9]
-
[10]
Yu, Chao and Velu, Akash and Vinitsky, Eugene and Gao, Jiaxuan and Wang, Yu and Bayen, Alexandre and Wu, Yi , month = jun, year =. The
- [11]
-
[12]
Treutlein, Johannes and Dennis, Michael and Oesterheld, Caspar and Foerster, Jakob , month = jul, year =. A. Proceedings of the 38th
- [13]
-
[14]
and Spaan, Matthijs T
Oliehoek, Frans A. and Spaan, Matthijs T. J. and Vlassis, Nikos , month = may, year =. Dec-
-
[15]
Expected
Muglich, Darius and Forkel, Johannes and Pol, Elise van der and Foerster, Jakob Nicolaus , month = oct, year =. Expected
-
[16]
, month = may, year =
Lucas, Keane and Allen, Ross E. , month = may, year =. Any-. Proceedings of the 21st
-
[17]
Hu, Hengyuan and Lerer, Adam and Cui, Brandon and Pineda, Luis and Brown, Noam and Foerster, Jakob , month = jul, year =. Off-. Proceedings of the 38th
-
[18]
Hu, Hengyuan and Lerer, Adam and Peysakhovich, Alex and Foerster, Jakob , month = nov, year =. “. Proceedings of the 37th
- [19]
-
[20]
Ruhdorfer, Constantin and Bortoletto, Matteo and Forkel, Johannes and Foerster, Jakob and Bulling, Andreas , month = mar, year =. The. doi:10.48550/arXiv.2508.12480 , abstract =
- [21]
- [22]
- [23]
- [24]
-
[25]
arXiv.org , author =
High entropy leads to symmetry equivariant policies in. arXiv.org , author =
-
[26]
Huang, Shengyi and Dossa, Rousslan Fernand Julien and Raffin, Antonin and Kanervisto, Anssi and Wang, Weixun , year =. The 37
- [27]
- [28]
-
[29]
doi:10.48550/arXiv.2602.18224 , abstract =
Luo, Yuankai and Chen, Woping and Liang, Tong and Wang, Baiqiao and Li, Zhenguo , month = feb, year =. doi:10.48550/arXiv.2602.18224 , abstract =
-
[30]
doi:10.48550/arXiv.2502.09560 , abstract =
Yang, Rui and Chen, Hanyang and Zhang, Junyu and Zhao, Mark and Qian, Cheng and Wang, Kangrui and Wang, Qineng and Koripella, Teja Venkat and Movahedi, Marziyeh and Li, Manling and Ji, Heng and Zhang, Huan and Zhang, Tong , month = jun, year =. doi:10.48550/arXiv.2502.09560 , ...
- [31]
- [32]
- [33]
-
[34]
doi:10.48550/arXiv.2602.13476 , abstract =
Hirose, Noriaki and Glossop, Catherine and Shah, Dhruv and Levine, Sergey , month = feb, year =. doi:10.48550/arXiv.2602.13476 , abstract =
- [35]
- [36]
-
[37]
Yang, Guang and Yang, Tianpei and Qiao, Jingwen and Wu, Yanqing and Huo, Jing and Chen, Xingguo and Gao, Yang , month = mar, year =. Multi-. doi:10.48550/arXiv.2512.03528 , abstract =
- [38]
-
[39]
Pezeshkpour, Pouya and Hruschka, Estevam , month = feb, year =. From. doi:10.48550/arXiv.2602.02760 , abstract =
-
[40]
Benchmarking
Ruan, Kai and Huang, Mowen and Wen, Ji-Rong and Sun, Hao , month = oct, year =. Benchmarking. doi:10.48550/arXiv.2505.04364 , abstract =
- [41]
-
[42]
Chen, Jingdi and Yang, Hanqing and Liu, Zongjun and Joe-Wong, Carlee , month = feb, year =. The. doi:10.48550/arXiv.2602.11583 , abstract =
-
[43]
doi:10.48550/arXiv.2510.26536 , abstract =
Tan, Huajie and Chi, Cheng and Chen, Xiansheng and Ji, Yuheng and Zhao, Zhongxia and Hao, Xiaoshuai and Lyu, Yaoxu and Cao, Mingyu and Zhao, Junkai and Lyu, Huaihai and Zhou, Enshen and Chen, Ning and Fu, Yankai and Peng, Cheng and Guo, Wei and Liang, Dong and Chen, Zhuo and L...
-
[44]
and Bishop, Hugh , year =
Bishop, Christopher M. and Bishop, Hugh , year =. Deep. doi:10.1007/978-3-031-45468-4 , keywords =
- [45]
- [46]
-
[47]
Wang, Kevin and Javali, Ishaan and Bortkiewicz, Michał , keywords =. 1000
-
[48]
Eckhaus, Niv and Berger, Uri and Stanovsky, Gabriel , month = sep, year =. Time to. doi:10.48550/arXiv.2506.05309 , abstract =
-
[49]
Cooperation
Nishimoto, Keita and Asatani, Kimitaka and Sakata, Ichiro , month = feb, year =. Cooperation. doi:10.48550/arXiv.2602.11754 , abstract =
-
[50]
State of
Reuss, Moritz , keywords =. State of
-
[51]
ScieNce RoboticS , author =
Learning a thousand tasks in a day , language =. ScieNce RoboticS , author =. 2025 , keywords =
2025
-
[52]
Trajectory
Lupu, Andrei and Cui, Brandon and Hu, Hengyuan and Foerster, Jakob , month = jul, year =. Trajectory. Proceedings of the 38th
- [53]
-
[54]
Zheng, Yujia and Zhao, Zhuokai and Li, Zijian and Xie, Yaqi and Gao, Mingze and Zhang, Lizhu and Zhang, Kun , month = oct, year =. Thought. doi:10.48550/arXiv.2510.20733 , abstract =
-
[55]
Vicinagearth , author =
A survey on. Vicinagearth , author =. 2024 , keywords =. doi:10.1007/s44336-024-00009-2 , abstract =
2024 doi
-
[56]
Blumenkamp, Jan and Morad, Steven and Gielis, Jennifer and Li, Qingbiao and Prorok, Amanda , month = may, year =. A. 2022. doi:10.1109/ICRA46639.2022.9811744 , abstract =
2022
-
[57]
and Mireshghallah, Niloofar and Ibrahim, Mark and Mahloujifar, Saeed , month = feb, year =
Morris, John X. and Mireshghallah, Niloofar and Ibrahim, Mark and Mahloujifar, Saeed , month = feb, year =. Learning to. doi:10.48550/arXiv.2602.04118 , abstract =
-
[58]
Elements of
Ben-Ari, Mordechai and Mondada, Francesco , year =. Elements of. doi:10.1007/978-3-319-62533-1 , language =
-
[59]
doi:10.48550/arXiv.2510.21450 , abstract =
Danieli, Federico and Rodriguez, Pau and Sarabia, Miguel and Suau, Xavier and Zappella, Luca , month = nov, year =. doi:10.48550/arXiv.2510.21450 , abstract =
- [60]
-
[61]
Robots in a human world: safety, reliability, robustness , abstract =
- [62]
-
[63]
IEEE Robotics and Automation Letters , author =
Learning-. IEEE Robotics and Automation Letters , author =. 2023 , pages =. doi:10.1109/LRA.2023.3234809 , abstract =
2023
-
[64]
doi:10.48550/arXiv.2510.04898 , abstract =
Xiong, Zheng and Li, Kang and Wang, Zilin and Jackson, Matthew and Foerster, Jakob and Whiteson, Shimon , month = oct, year =. doi:10.48550/arXiv.2510.04898 , abstract =
-
[65]
Wan, Weikang and Zhu, Yifeng and Shah, Rutav and Zhu, Yuke , month = may, year =. 2024. doi:10.1109/ICRA57147.2024.10611129 , abstract =
2024
-
[66]
Nature , author =
Loss of plasticity in deep continual learning , volume =. Nature , author =. 2024 , pages =. doi:10.1038/s41586-024-07711-7 , abstract =
2024 doi
- [67]
-
[68]
Robotics and Autonomous Systems , author =
Perceived safety in physical human–robot interaction—. Robotics and Autonomous Systems , author =. 2022 , pages =. doi:10.1016/j.robot.2022.104047 , abstract =
2022
-
[69]
Foundation models: toward real-robot and real-time capable systems , abstract =
- [70]
- [71]
- [72]
- [73]
-
[74]
and Kailkhura, Bhavya and Bhatele, Abhinav and Goldstein, Tom , month = feb, year =
Geiping, Jonas and McLeish, Sean and Jain, Neel and Kirchenbauer, John and Singh, Siddharth and Bartoldson, Brian R. and Kailkhura, Bhavya and Bhatele, Abhinav and Goldstein, Tom , month = feb, year =. Scaling up. doi:10.48550/arXiv.2502.05171 , abstract =
-
[75]
2025 , keywords =
Enabling. 2025 , keywords =
2025
- [77]
-
[78]
Entropy is all you need for
-
[79]
IEEE Transactions on Pattern Analysis and Machine Intelligence , author =
A. IEEE Transactions on Pattern Analysis and Machine Intelligence , author =. 2024 , pages =. doi:10.1109/TPAMI.2024.3457538 , abstract =
2024
-
[80]
Language
Radford, Alec and Wu, Jeffrey and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya , keywords =. Language
-
[81]
Improving
Radford, Alec and Narasimhan, Karthik and Salimans, Tim and Sutskever, Ilya , keywords =. Improving
- [82]
- [83]
- [84]
-
[85]
Journal of Automation and Intelligence , author =
A survey on multi-agent reinforcement learning and its application , volume =. Journal of Automation and Intelligence , author =. 2024 , keywords =. doi:10.1016/j.jai.2024.02.003 , abstract =
2024 doi
-
[86]
Albrecht, Stefano V and Christianos, Filippos and Schäfer, Lukas , keywords =. Multi-
-
[87]
Proceedings of the 2019
Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina , editor =. Proceedings of the 2019. 2019 , keywords =. doi:10.18653/v1/N19-1423 , abstract =
2019 doi
-
[88]
Language
Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and Agarwal, Sandhini and Herbert-Voss, Ariel and Krueger, Gretchen and Henighan, Tom a...
- [89]
- [90]
- [91]
- [92]
-
[93]
IEEE Robotics and Automation Letters , author =
Automated. IEEE Robotics and Automation Letters , author =. 2026 , keywords =. doi:10.1109/LRA.2025.3643276 , abstract =
2026
-
[94]
Li, Chenhao and Krause, Andreas and Hutter, Marco , month = dec, year =. Robotic. doi:10.48550/arXiv.2501.10100 , abstract =
-
[95]
Evolution
Sarkar, Bidipta and Fellows, Mattie and Duque, Juan Agustin and Letcher, Alistair and Villares, Antonio León and Sims, Anya and Cope, Dylan and Liesen, Jarek and Seier, Lukas and Wolf, Theo and Berdica, Uljad and Goldie, Alexander David and Courville, Aaron and Sevegnani, Kari...
-
[96]
Raschka, Sebastian , month = feb, year =. The
- [97]
-
[98]
Li, Hao Xiang and Amir, Michael and Prorok, Amanda , year =
- [99]
-
[100]
doi:10.48550/arXiv.2505.03912 , abstract =
Cui, Can and Ding, Pengxiang and Song, Wenxuan and Bai, Shuanghao and Tong, Xinyang and Ge, Zirui and Suo, Runze and Zhou, Wanqi and Liu, Yang and Jia, Bofang and Zhao, Han and Huang, Siteng and Wang, Donglin , month = may, year =. doi:10.48550/arXiv.2505.03912 , abstract =
- [101]
-
[102]
and Kumar, Vijay , month = oct, year =
Ravichandran, Zachary and Hounie, Ignacio and Cladera, Fernando and Ribeiro, Alejandro and Pappas, George J. and Kumar, Vijay , month = oct, year =. Distilling. doi:10.48550/arXiv.2506.17486 , abstract =
-
[103]
Amir, Michael and Bettini, Matteo and Prorok, Amanda , month = sep, year =. When. doi:10.48550/arXiv.2506.09434 , abstract =
- [104]
- [105]
-
[106]
, month = sep, year =
Hu, Hengyuan and Foerster, Jakob N. , month = sep, year =. Simplified
-
[107]
AMR Lab , author =
Decentralized. AMR Lab , author =
- [108]
- [109]
-
[110]
Carroll, Micah and Shah, Rohin and Ho, Mark K and Griffiths, Tom and Seshia, Sanjit and Abbeel, Pieter and Dragan, Anca , year =. On the. Advances in
- [111]
- [113]
-
[114]
and Aodha, Oisin Mac and Foerster, Jakob and Bachrach, Yoram , month = jun, year =
Zhao, Bingchen and Magka, Despoina and Jiang, Minqi and Li, Xian and Raileanu, Roberta and Shavrina, Tatiana and Gagnon-Audet, Jean-Christophe and Niu, Kelvin and Sodhani, Shagun and Shvartsman, Michael and Lupu, Andrei and Lupidi, Alisia and Toledo, Edan and Hambardzumyan, Ka...
-
[115]
Controlling diverse robots by inferring
Li, Sizhe Lester and Zhang, Annan and Chen, Boyuan and Matusik, Hanna and Liu, Chao and Rus, Daniela and Sitzmann, Vincent , month = jul, year =. Controlling diverse robots by inferring. Nature , publisher =. doi:10.1038/s41586-025-09170-0 , abstract =
- [117]
-
[118]
Alex and Humplik, Jan and Iscen, Atil and Jacob, Mithun George and Jain, Deepali and Julian, Ryan and Kalashnikov, Dmitry and Karagozler, M
Team, Gemini Robotics and Abeyruwan, Saminda and Ainslie, Joshua and Alayrac, Jean-Baptiste and Arenas, Montserrat Gonzalez and Armstrong, Travis and Balakrishna, Ashwin and Baruch, Robert and Bauza, Maria and Blokzijl, Michiel and Bohez, Steven and Bousmalis, Konstantinos and...
- [119]
- [120]
-
[121]
Machine Learning , author =
Q-learning , volume =. Machine Learning , author =. 1992 , keywords =. doi:10.1007/BF00992698 , language =
1992 doi
- [122]
-
[123]
Compiling machine learning programs via high-level tracing , abstract =
Frostig, Roy and Johnson, Matthew James and Leary, Chris , year =. Compiling machine learning programs via high-level tracing , abstract =
-
[124]
SoftwareX , author =
Discovering and exploring cases of educational source code plagiarism with. SoftwareX , author =. 2024 , keywords =. doi:10.1016/j.softx.2024.101755 , language =
2024
-
[125]
Machine Learning , author =
Simple statistical gradient-following algorithms for connectionist reinforcement learning , volume =. Machine Learning , author =. 1992 , keywords =. doi:10.1007/BF00992696 , abstract =
1992 doi
-
[126]
and Hunt, Jonathan J
Lillicrap, Timothy P. and Hunt, Jonathan J. and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan , month = jul, year =. Continuous control with deep reinforcement learning , url =. doi:10.48550/arXiv.1509.02971 , abstract =
-
[127]
2024 , keywords =
Journal of Information and Intelligence , author =. 2024 , keywords =. doi:10.1016/j.jiixd.2023.10.002 , abstract =
2024 doi
- [128]
- [129]
-
[130]
Efficient memory-based learning for robot control , language =
Moore, Andrew William , year =. Efficient memory-based learning for robot control , language =
-
[131]
IEEE Transactions on Systems, Man, and Cybernetics , author =
Neuronlike adaptive elements that can solve difficult learning control problems , volume =. IEEE Transactions on Systems, Man, and Cybernetics , author =. 1983 , note =. doi:10.1109/TSMC.1983.6313077 , abstract =
1983
- [132]
-
[133]
Gauthier, Paul , note =. Aider:
-
[134]
Oliehoek, Frans and Amato, Christopher , month = jan, year =. A. doi:10.1007/978-3-319-28929-8 , abstract =
-
[135]
Sutton, Richard S and McAllester, David and Singh, Satinder and Mansour, Yishay , year =. Policy. Advances in
- [136]
- [137]
-
[138]
Artificial Intelligence , author =
Planning and acting in partially observable stochastic domains , volume =. Artificial Intelligence , author =. 1998 , keywords =. doi:10.1016/S0004-3702(98)00023-X , abstract =
1998 doi
-
[139]
and Wettig, Alexander and Lieret, Kilian and Yao, Shunyu and Narasimhan, Karthik and Press, Ofir , month = nov, year =
Yang, John and Jimenez, Carlos E. and Wettig, Alexander and Lieret, Kilian and Yao, Shunyu and Narasimhan, Karthik and Press, Ofir , month = nov, year =. doi:10.48550/arXiv.2405.15793 , abstract =
- [140]
- [141]
- [142]
- [143]
-
[144]
and Tang, Xiangru and Zhuge, Mingchen and Pan, Jiayi and Song, Yueqi and Li, Bowen and Singh, Jaskirat and Tran, Hoang H
Wang, Xingyao and Li, Boxuan and Song, Yufan and Xu, Frank F. and Tang, Xiangru and Zhuge, Mingchen and Pan, Jiayi and Song, Yueqi and Li, Bowen and Singh, Jaskirat and Tran, Hoang H. and Li, Fuqiang and Ma, Ren and Zheng, Mingzhang and Qian, Bill and Shao, Yanjun and Muennigh...
- [145]
- [146]
- [147]
- [148]
- [149]
- [150]
- [151]
-
[152]
doi:10.48550/arXiv.2308.00352 , abstract =
Hong, Sirui and Zhuge, Mingchen and Chen, Jiaqi and Zheng, Xiawu and Cheng, Yuheng and Zhang, Ceyao and Wang, Jinlin and Wang, Zili and Yau, Steven Ka Shing and Lin, Zijuan and Zhou, Liyang and Ran, Chenyu and Xiao, Lingfeng and Wu, Chenglin and Schmidhuber, Jürgen , month = n...
-
[153]
Competition-level code generation with
- [154]
- [155]
-
[156]
doi:10.48550/arXiv.2307.07924 , abstract =
Qian, Chen and Liu, Wei and Liu, Hongzhang and Chen, Nuo and Dang, Yufan and Li, Jiahao and Yang, Cheng and Chen, Weize and Su, Yusheng and Cong, Xin and Xu, Juyuan and Li, Dahai and Liu, Zhiyuan and Sun, Maosong , month = jun, year =. doi:10.48550/arXiv.2307.07924 , abstract =
-
[157]
and Hutter, Frank and Leyton-Brown, Kevin , editor =
Kotthoff, Lars and Thornton, Chris and Hoos, Holger H. and Hutter, Frank and Leyton-Brown, Kevin , editor =. Auto-. Automated. 2019 , note =. doi:10.1007/978-3-030-05318-5_4 , abstract =
2019 doi
-
[158]
and Moore, Jason H
Olson, Randal S. and Moore, Jason H. , editor =. Automated. 2019 , note =. doi:10.1007/978-3-030-05318-5_8 , abstract =
2019 doi
-
[159]
LeDell, E and Poirier, S , keywords =
-
[160]
and Bao, Han and Xu, Hanwei and Wang, Haocheng and Zhang, Haowei and Ding, Honghui and Xin, Huajian and Gao, Huazuo and Li, Hui and Qu, Hui and Cai, J
DeepSeek-AI and Liu, Aixin and Feng, Bei and Xue, Bing and Wang, Bingxuan and Wu, Bochao and Lu, Chengda and Zhao, Chenggang and Deng, Chengqi and Zhang, Chenyu and Ruan, Chong and Dai, Damai and Guo, Daya and Yang, Dejian and Chen, Deli and Ji, Dongjie and Li, Erhang and Lin,...
- [161]
- [162]
- [163]
- [164]
-
[165]
Efficient and
Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina and Springenberg, Jost and Blum, Manuel and Hutter, Frank , year =. Efficient and. Advances in
-
[166]
doi:10.48550/arXiv.2410.07095 , abstract =
Chan, Jun Shern and Chowdhury, Neil and Jaffe, Oliver and Aung, James and Sherburn, Dane and Mays, Evan and Starace, Giulio and Liu, Kevin and Maksin, Leon and Patwardhan, Tejal and Weng, Lilian and Mądry, Aleksander , month = feb, year =. doi:10.48550/arXiv.2410.07095 , abstract =
- [167]
- [168]
-
[169]
doi:10.48550/arXiv.2502.14499 , abstract =
Nathani, Deepak and Madaan, Lovish and Roberts, Nicholas and Bashlykov, Nikolay and Menon, Ajay and Moens, Vincent and Budhiraja, Amar and Magka, Despoina and Vorotilov, Vladislav and Chaurasia, Gaurav and Hupkes, Dieuwke and Cabral, Ricardo Silveira and Shavrina, Tatiana and ...
-
[170]
and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik , month = nov, year =
Jimenez, Carlos E. and Yang, John and Wettig, Alexander and Yao, Shunyu and Pei, Kexin and Press, Ofir and Narasimhan, Karthik , month = nov, year =. doi:10.48550/arXiv.2310.06770 , abstract =
-
[171]
LeCun, Yann , keywords =. A
- [172]
-
[173]
Benchmarking
Huang, Qian and Vora, Jian and Liang, Percy and Leskovec, Jure , month = oct, year =. Benchmarking
- [174]
- [175]
- [176]
- [177]
- [178]
-
[179]
doi:10.48550/arXiv.2308.03688 , abstract =
Liu, Xiao and Yu, Hao and Zhang, Hanchen and Xu, Yifan and Lei, Xuanyu and Lai, Hanyu and Gu, Yu and Ding, Hangliang and Men, Kaiwen and Yang, Kejuan and Zhang, Shudan and Deng, Xiang and Zeng, Aohan and Du, Zhengxiao and Zhang, Chenhui and Shen, Sheng and Zhang, Tianjun and S...
-
[180]
doi:10.48550/arXiv.2403.16443 , abstract =
Zan, Daoguang and Yu, Ailun and Liu, Wei and Chen, Dong and Shen, Bo and Li, Wei and Yao, Yafen and Gong, Yongshun and Chen, Xiaolin and Guan, Bei and Yang, Zhiguang and Wang, Yongji and Wang, Qianxiang and Cui, Lizhen , month = mar, year =. doi:10.48550/arXiv.2403.16443 , abstract =
-
[181]
and Iyer, Arun and Parthasarathy, Suresh and Rajamani, Sriram and Ashok, B
Bairi, Ramakrishna and Sonwane, Atharv and Kanade, Aditya and C, Vageesh D. and Iyer, Arun and Parthasarathy, Suresh and Rajamani, Sriram and Ashok, B. and Shet, Shashank , month = sep, year =. doi:10.48550/arXiv.2309.12499 , abstract =
- [182]
-
[183]
Quality-
Dharna, Aaron and Lu, Cong and Clune, Jeff , keywords =. Quality-
- [184]
- [185]
- [186]
- [187]
- [188]
- [189]
- [190]
- [191]
- [192]
- [193]
- [194]
- [195]
- [196]
- [197]
- [198]
-
[199]
Liu, Minghuan and Zhu, Menghui and Zhang, Weinan , month = jul, year =. Goal-. Proceedings of the. doi:10.24963/ijcai.2022/770 , abstract =
2022 doi
-
[200]
Language to
Yu, Wenhao and Gileadi, Nimrod and Fu, Chuyuan and Kirmani, Sean and Lee, Kuang-Huei and Arenas, Montse Gonzalez and Chiang, Hao-Tien Lewis and Erez, Tom and Hasenclever, Leonard and Humplik, Jan and Ichter, Brian and Xiao, Ted and Xu, Peng and Zeng, Andy and Zhang, Tingnan an...
- [201]
- [202]
-
[203]
IEEE Transactions on Vehicular Technology , author =
Multi-. IEEE Transactions on Vehicular Technology , author =. 2020 , note =. doi:10.1109/TVT.2020.2997896 , abstract =
2020
-
[204]
Proceedings of the 36th
Das, Abhishek and Gervet, Théophile and Romoff, Joshua and Batra, Dhruv and Parikh, Devi and Rabbat, Mike and Pineau, Joelle , month = may, year =. Proceedings of the 36th
-
[205]
Schester, Larry , month = aug, year =. Multi-. doi:10.7302/7998 , abstract =
-
[206]
IEEE Access , author =
Joint. IEEE Access , author =. 2019 , note =. doi:10.1109/ACCESS.2019.2943253 , abstract =
2019
- [207]
-
[208]
ANYbotics , author =
Superior. ANYbotics , author =
-
[209]
Champion-level drone racing using deep reinforcement learning , volume =
Kaufmann, Elia and Bauersfeld, Leonard and Loquercio, Antonio and Müller, Matthias and Koltun, Vladlen and Scaramuzza, Davide , month = aug, year =. Champion-level drone racing using deep reinforcement learning , volume =. Nature , publisher =. doi:10.1038/s41586-023-06419-4 ,...
-
[210]
and Barto, Andrew , year =
Sutton, Richard S. and Barto, Andrew , year =. Reinforcement learning: an introduction , isbn =
-
[211]
, month = nov, year =
Zeng, Fanlong and Gan, Wensheng and Wang, Yongheng and Liu, Ning and Yu, Philip S. , month = nov, year =. Large
- [212]
- [213]
- [214]
-
[215]
Design of a home multi-robot system for the elderly and disabled , isbn =
Benavidez, Patrick and Kumar, Mohan and Agaian, Sos and Jamshidi, Mo , month = may, year =. Design of a home multi-robot system for the elderly and disabled , isbn =. 2015 10th. doi:10.1109/SYSOSE.2015.7151907 , abstract =
2015
-
[217]
Tan, Ming , year =. Multi-. Machine. doi:10.1016/B978-1-55860-307-3.50049-6 , language =
-
[218]
doi:10.1145/3308558.3314139 , abstract =
Zhang, Huichu and Feng, Siyuan and Liu, Chang and Ding, Yaoyao and Zhu, Yichen and Zhou, Zihan and Zhang, Weinan and Yu, Yong and Jin, Haiming and Li, Zhenhui , year =. doi:10.1145/3308558.3314139 , abstract =
- [219]
- [220]
- [221]
- [222]
-
[223]
doi:10.48550/arXiv.2308.05960 , abstract =
Liu, Zhiwei and Yao, Weiran and Zhang, Jianguo and Xue, Le and Heinecke, Shelby and Murthy, Rithesh and Feng, Yihao and Chen, Zeyuan and Niebles, Juan Carlos and Arpit, Devansh and Xu, Ran and Mui, Phil and Wang, Huan and Xiong, Caiming and Savarese, Silvio , month = aug, year...
-
[224]
and Stone, Austin and Kappler, Daniel , month = oct, year =
Chen, Boyuan and Xia, Fei and Ichter, Brian and Rao, Kanishka and Gopalakrishnan, Keerthana and Ryoo, Michael S. and Stone, Austin and Kappler, Daniel , month = oct, year =. Open-vocabulary. doi:10.48550/arXiv.2209.09874 , abstract =
- [225]
- [226]
-
[227]
IEEE Robotics and Automation Letters , author =
Integrated. IEEE Robotics and Automation Letters , author =. 2021 , note =. doi:10.1109/LRA.2021.3074883 , abstract =
2021
- [228]
-
[229]
doi:10.48550/arXiv.2307.08962 , abstract =
Murthy, Rithesh and Heinecke, Shelby and Niebles, Juan Carlos and Liu, Zhiwei and Xue, Le and Yao, Weiran and Feng, Yihao and Chen, Zeyuan and Gokul, Akash and Arpit, Devansh and Xu, Ran and Mui, Phil and Wang, Huan and Xiong, Caiming and Savarese, Silvio , month = jan, year =...
- [230]
-
[231]
IEEE Access , author =
Collaborative. IEEE Access , author =. 2020 , note =. doi:10.1109/ACCESS.2020.3030190 , abstract =
2020
- [232]
- [233]
- [234]
- [236]
-
[237]
Graphcomm:
Shen, Siqi and Fu, Yongquan and Su, Huayou and Pan, Hengyue and Qiao, Peng and Dou, Yong and Wang, Cheng , month = jun, year =. Graphcomm:. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , publisher =. doi:10.1109/ICASSP397...
2021
- [238]
- [239]
- [240]
- [241]
- [242]
-
[243]
Language as an
Jiang, YiDing and Gu, Shixiang (Shane) and Murphy, Kevin P and Finn, Chelsea , year =. Language as an. Advances in
-
[244]
Proceedings of the AAAI Conference on Artificial Intelligence , author =
Conceptual. Proceedings of the AAAI Conference on Artificial Intelligence , author =. 2023 , note =. doi:10.1609/aaai.v37i8.26129 , abstract =
2023 doi
- [245]
-
[246]
Sadhu, Vidyasagar and Sun, Chuanneng and Karimian, Arman and Tron, Roberto and Pompili, Dario , month = dec, year =. Aerial-. doi:10.1109/MASS50613.2020.00030 , abstract =
2020
-
[247]
Scalable
Chen, Yongchao and Arkin, Jacob and Zhang, Yang and Roy, Nicholas and Fan, Chuchu , month = mar, year =. Scalable
- [248]
- [249]
- [250]
- [251]
-
[252]
Sun, Chuanneng and Huang, Songjun and Pompili, Dario , month = may, year =
- [253]
-
[254]
Multi-agent
Huh, Dom and Mohapatra, Prasant , month = jul, year =. Multi-agent
-
[255]
Artificial Intelligence Review , author =
Multi-agent deep reinforcement learning: a survey , volume =. Artificial Intelligence Review , author =. 2022 , keywords =. doi:10.1007/s10462-021-09996-w , abstract =
2022 doi
- [256]
-
[257]
and Li, Qingbiao and Prorok, Amanda and Ribeiro, Alejandro and Tokekar, Pratap and Kumar, Vijay , month = sep, year =
Zhou, Lifeng and Sharma, Vishnu D. and Li, Qingbiao and Prorok, Amanda and Ribeiro, Alejandro and Tokekar, Pratap and Kumar, Vijay , month = sep, year =. Graph. doi:10.48550/arXiv.2105.08601 , abstract =
-
[258]
Blumenkamp, Jan and Morad, Steven and Gielis, Jennifer and Prorok, Amanda , month = oct, year =
- [259]
-
[260]
and Gmytrasiewicz, P
Doshi, P. and Gmytrasiewicz, P. J. , month = sep, year =. A
-
[261]
Artificial Intelligence , author =
The. Artificial Intelligence , author =. 2020 , keywords =. doi:10.1016/j.artint.2019.103216 , language =
2020
-
[262]
Jackson, Matthew Thomas and Matthews, Michael Tryfan and Lu, Cong and Ellis, Benjamin and Whiteson, Shimon and Foerster, Jakob , month = apr, year =. Policy-
-
[263]
Discovering
Jackson, Matthew Thomas and Lu, Chris and Kirsch, Louis and Lange, Robert Tjarko and Whiteson, Shimon and Foerster, Jakob Nicolaus , month = feb, year =. Discovering
- [264]
-
[265]
Pan, Haotian and Huang, Shibo and Yang, Jian and Mi, Jinpeng and Li, Ke and You, Xiong and Tang, Xuan and Liang, Peidong and Yang, Jinbo and Liu, Yingjie and Zhang, Jianfeng and Wang, Muyu and Yang, Jie and Zhang, Xinyu and Zhao, Lijun and Chen, Mingsong and Zhou, Jie and Wei,...
- [266]
- [267]
- [268]
- [269]
- [270]
- [271]
-
[272]
Proceedings of the
Chen, Guangyao and Dong, Siwei and Shu, Yu and Zhang, Ge and Sesay, Jaward and Karlsson, Börje and Fu, Jie and Shi, Yemin , month = aug, year =. Proceedings of the. doi:10.24963/ijcai.2024/3 , abstract =
2024 doi
-
[273]
and Wiest, Olaf and Zhang, Xiangliang , month = apr, year =
Guo, Taicheng and Chen, Xiuying and Wang, Yaqi and Chang, Ruidi and Pei, Shichao and Chawla, Nitesh V. and Wiest, Olaf and Zhang, Xiangliang , month = apr, year =. Large
-
[274]
Zhang, Yadong and Mao, Shaoguang and Ge, Tao and Wang, Xun and Wynter, Adrian de and Xia, Yan and Wu, Wenshan and Song, Ting and Lan, Man and Wei, Furu , month = apr, year =
- [275]
- [276]
-
[277]
, month = mar, year =
Xu, Xinrun and Wang, Yuxin and Xu, Chaoyi and Ding, Ziluo and Jiang, Jiechuan and Ding, Zhiming and Karlsson, Börje F. , month = mar, year =. A
-
[278]
Hierarchical
Zhao, Zhonghan and Chen, Kewei and Guo, Dongxu and Chai, Wenhao and Ye, Tian and Zhang, Yanting and Wang, Gaoang , month = mar, year =. Hierarchical
- [279]
-
[280]
, year =
Henrique da Silva, Heitor and Rocha, Michele and Trajano, Guilherme and Schiaffino Morales, Analúcia and Sarkadi, Stefan and Panisson, Alison R. , year =. Distributed. 16th
- [281]
- [282]
-
[283]
Hu, Sihao and Huang, Tiansheng and Ilhan, Fatih and Tekin, Selim and Liu, Gaowen and Kompella, Ramana and Liu, Ling , month = apr, year =. A
-
[284]
Suspicion-
Guo, Jiaxian and Yang, Bo and Yoo, Paul and Lin, Bill Yuchen and Iwasawa, Yusuke and Matsuo, Yutaka , month = aug, year =. Suspicion-
-
[285]
Agashe, Saaket and Fan, Yue and Reyna, Anthony and Wang, Xin Eric , month = apr, year =
-
[286]
Learning to
Jin, Xuanfa and Wang, Ziyan and Du, Yali and Fang, Meng and Zhang, Haifeng and Wang, Jun , month = may, year =. Learning to
-
[287]
Sims, Anya and Lu, Cong and Teh, Yee Whye , month = feb, year =. The
- [288]
-
[289]
Theory of
Li, Huao and Chong, Yu and Stepputtis, Simon and Campbell, Joseph and Hughes, Dana and Lewis, Charles and Sycara, Katia , year =. Theory of. Proceedings of the 2023. doi:10.18653/v1/2023.emnlp-main.13 , abstract =
2023 doi
-
[290]
doi:10.1007/978-3-031-45368-7 , language =
Intelligent. doi:10.1007/978-3-031-45368-7 , language =
-
[291]
Bhardwaj, Arjun and Rothfuss, Jonas and Sukhija, Bhavya and As, Yarden and Hutter, Marco and Coros, Stelian and Krause, Andreas , month = feb, year =. Data-
-
[292]
Simplifying
Gallici, Matteo and Fellows, Mattie and Ellis, Benjamin and Pou, Bartomeu and Masmitja, Ivan and Foerster, Jakob Nicolaus and Martin, Mario , month = oct, year =. Simplifying
- [293]
- [294]
- [295]
- [296]
- [297]
- [298]
-
[299]
Proceedings of the AAAI Conference on Artificial Intelligence , author =
When. Proceedings of the AAAI Conference on Artificial Intelligence , author =. 2018 , keywords =. doi:10.1609/aaai.v32i1.11831 , abstract =
2018 doi
-
[300]
Long, Qian and Li, Ruoyan and Zhao, Minglu and Gao, Tao and Terzopoulos, Demetri , month = oct, year =. Inverse
Reviewed August 5, 2026 · model on record in the stance chip above.
Discussion (0). Sign in to comment.