Language-Induced Priors from LLMs guide source selection in cold-start domain adaptation through an EM algorithm, matching oracle MSE under a correct prior and remaining asymptotically consistent.
hub
International conference on machine learning , pages=
26 Pith papers cite this work. Polarity classification is still indexing.
26
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 26roles
background 1polarities
background 1representative citing papers
The paper establishes the first tilde O(epsilon^{-1}) upper bounds and matching lower bounds for forward-KL-regularized offline contextual bandits under single-policy concentrability in both tabular and general function approximation settings.
DTSemNet gives an exact, invertible neural-network encoding of hard oblique decision trees that supports direct gradient training for both classification and regression without probabilistic softening or quantized estimators.
Deceptive Meta Planning (DeMP) uses two-level optimization to sustain deception against learning observers by combining short-term adaptation with meta-level learning of observer updates.
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
ScenePilot uses RSS-derived physical feasibility score and online-learned AV-risk predictor in constrained RL with feasibility-aware shielding to generate boundary-band scenarios, yielding +6.2 pp higher collision rates on SafeBench while preserving validity.
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
Reinforcement learning agent trained in DIII-D tokamak simulator achieves 2.01 cm mean shape error on held-out data, tracks dynamic targets, and remains functional under 30% random sensor dropout with direct transfer to experimental shots.
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
HölderPO unifies token-level aggregation in GRPO via the Hölder mean with a tunable p parameter and annealing schedule, delivering 54.9% average accuracy on math benchmarks and 93.8% success on ALFWorld.
OPEFO prevents entropy collapse in RLVR by rescaling token updates according to their entropy change contributions, yielding more stable optimization and better results on math benchmarks.
Geometric Pareto Control embeds Pareto solutions in a Lie group submanifold and navigates via Riemannian gradient flow to achieve 100% feasibility and low suboptimality in control tasks without retraining.
TRIRL uses a trust-region insight to allow explicit dual ascent in IRL with local policy searches, claiming monotonic improvement and better generalization than prior methods.
Listwise Policy Optimization explicitly performs target-projection on the LLM response simplex, unifying and improving group-based RLVR methods with monotonic improvement and flexible divergences.
Q2RL extracts Q-values from a BC policy and applies Q-gating to enable efficient offline-to-online RL, outperforming baselines on D4RL/robomimic tasks and achieving up to 100% success on real-robot manipulation in 1-2 hours.
OGPO enables sample-efficient full-finetuning of generative control policies via off-policy critics and modified PPO, achieving SOTA on robot manipulation tasks while rescuing poorly initialized behavior cloning policies without expert data.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
Regulation Zero 2 applies hierarchical MCTS with a local proposal engine and FPFS reward estimation to optimize sequences of flow regulations in ATFM, outperforming flight-centric baselines while limiting network impact.
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
Dual-Window Smoothing uses an execution window for deterministic smoothness and a value window to correct critic bias, plus a first-order temporal regularizer, to achieve smoother RL control than explicit chunking or standard baselines.
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
MATE uses permutation-invariant sum-aggregated memory of transition embeddings to solve CMDPs with online adaptation and computational advantages over Transformers and RNNs.
QuantFPFlow uses quantum amplitude estimation in a Fokker-Planck RL framework to achieve O(1/ε) partition function estimation and reports improved global optimum discovery plus better scaling in continuous control tasks.
citing papers explorer
-
Dynamic Plasma Shape Control with Arbitrary Sensor Subsets
Reinforcement learning agent trained in DIII-D tokamak simulator achieves 2.01 cm mean shape error on held-out data, tracks dynamic targets, and remains functional under 30% random sensor dropout with direct transfer to experimental shots.
-
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
Q2RL extracts Q-values from a BC policy and applies Q-gating to enable efficient offline-to-online RL, outperforming baselines on D4RL/robomimic tasks and achieving up to 100% success on real-robot manipulation in 1-2 hours.
-
Implicit Action Chunking for Smooth Continuous Control
Dual-Window Smoothing uses an execution window for deterministic smoothness and a value window to correct critic bias, plus a first-order temporal regularizer, to achieve smoother RL control than explicit chunking or standard baselines.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
Transfer Learning for Customized Car Racing Environments
The study applies transfer learning to deep RL in OpenAI car racing, observing that model-based approaches outperform model-free methods and that transfer boosts target domain performance.