Pith. sign in

REVIEW 14 cited by

Transformers are Sample-Efficient World Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.00588 v2 pith:LZZVK5BO submitted 2022-09-01 cs.LG cs.AIcs.CV

classification cs.LGcs.AIcs.CV
keywords worldirislearningmodelmodelstransformersmethodsreinforcement
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the imagination of a world model being one of the most prominent approaches. However, while virtually unlimited interaction with a simulated environment sounds appealing, the world model has to be accurate over extended periods of time. Motivated by the success of Transformers in sequence modeling tasks, we introduce IRIS, a data-efficient agent that learns in a world model composed of a discrete autoencoder and an autoregressive Transformer. With the equivalent of only two hours of gameplay in the Atari 100k benchmark, IRIS achieves a mean human normalized score of 1.046, and outperforms humans on 10 out of 26 games, setting a new state of the art for methods without lookahead search. To foster future research on Transformers and world models for sample-efficient reinforcement learning, we release our code and models at https://github.com/eloialonso/iris.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.

  2. Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    ADWM learns a latent diffusion world model with per-transition independent denoising and policy-conditioned guidance to enable accurate offline evaluation of LLM agent policies.

  3. Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution

    cs.RO 2025-08 conditional novelty 6.0 of 10

    Latent Policy Barrier improves behavior-cloned visuomotor policies by using a latent dynamics model trained on expert and rollout data to guide actions back toward in-distribution expert states.

  4. Dyn-O: Building Structured World Models with Object-Centric Representations

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Dyn-O learns object-centric world models directly from pixels in complex Procgen games, using SAM2-guided slot attention and Mamba state-space dynamics, and reports better rollout prediction than DreamerV3.

  5. ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation

    cs.RO 2025-06 conditional novelty 6.0 of 10

    ParticleFormer uses a Transformer over point-cloud particles and a hybrid Chamfer-Hausdorff loss to predict multi-material object dynamics, and it reports lower errors than GNN and image-based baselines in simulation ...

  6. EgoM2P: Egocentric Multimodal Multitask Pretraining

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A masked pretraining model over RGB, depth, gaze, and camera-pose tokens matches specialist egocentric vision systems on four tasks while running at 300+ frames per second.

  7. Quo Vadis, World Modeling?

    cs.CV 2026-08 conditional novelty 5.0 of 10

    An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.

  8. LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback

    cs.AI 2026-07 conditional novelty 5.0 of 10

    LEMUR jointly learns a separate reward model for each teacher's preferences and uses them to train a population of multi-objective policies, beating baselines that merge feedback into one reward.

  9. RynnVLA-002: A Unified Vision-Language-Action and World Model

    cs.RO 2025-11 conditional novelty 5.0 of 10

    A single model that jointly predicts robot actions and future images outperforms separate action-only and video-only models on LIBERO and real SO100 manipulation tasks.

  10. Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

    cs.LG 2025-10 conditional novelty 5.0 of 10

    In an RL-trained transformer solving adjacent-swap sorting, larger embedding dimensions improve the monotonicity of an internal order-encoding in attention weights and the match to a largest-adjacent-difference swap r...

  11. TransZero: Parallel Tree Expansion in MuZero using Transformer Networks

    cs.LG 2025-09 conditional novelty 4.0 of 10

    TransZero parallelizes Monte Carlo tree search expansion using a transformer dynamics network and a variance-based evaluator, achieving up to an 11x wall-clock speedup over MuZero without sacrificing final reward.

  12. Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning

    cs.RO 2025-08 reject novelty 4.0 of 10

    A review that categorizes large-model-empowered embodied AI into hierarchical and end-to-end decision-making, imitation and reinforcement learning, and world models.

  13. TransDreamerV3: Implanting Transformer In DreamerV3

    cs.LG 2025-06 reject novelty 4.0 of 10

    TransDreamerV3 replaces DreamerV3's GRU memory with a simple transformer encoder and reports mixed gains on four Atari and Crafter tasks.

  14. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0 of 10

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.

Pith tools