Transformer-based World Models Are Happy With 100k Interactions
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RY3RMCDYrecord.jsonopen to challenge →
read the original abstract
Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient world model, we apply a transformer to real-world episodes in an autoregressive manner: not only the compact latent states and the taken actions but also the experienced or predicted rewards are fed into the transformer, so that it can attend flexibly to all three modalities at different time steps. The transformer allows our world model to access previous states directly, instead of viewing them through a compressed recurrent state. By utilizing the Transformer-XL architecture, it is able to learn long-term dependencies while staying computationally efficient. Our transformer-based world model (TWM) generates meaningful, new experience, which is used to train a policy that outperforms previous model-free and model-based reinforcement learning algorithms on the Atari 100k benchmark.
This paper has not been read by Pith yet.
Forward citations
Cited by 17 Pith papers
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
SVI-Bench provides 35K hours of sports video with 9 tasks across four cognitive levels, revealing models drop from ~74% on action QA to 5% on agentic evidence integration.
-
JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning
JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampli...
-
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
ACO-MoE employs agent-centric mixture-of-experts to decouple task-relevant features from dynamic visual perturbations in RL, recovering 95.3% of clean performance on the new VDCS benchmark.
-
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
-
Advantage-Guided Diffusion for Model-Based Reinforcement Learning
Advantage-guided diffusion (SAG and EAG) steers sampling in diffusion world models to higher-advantage trajectories, enabling policy improvement and better sample efficiency on MuJoCo tasks.
-
Training Agents Inside of Scalable World Models
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
-
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
SVI-Bench is a 35K-hour sports video benchmark with 9 tasks across four cognitive pillars that reveals multimodal models drop from ~73% on action QA to 5% on agentic evidence-gathering tasks.
-
Self-supervised Hierarchical Visual Reasoning with World Model
ResDreamer proposes a residual-based hierarchical world model for purely self-supervised visual foresight reasoning that scales with linear communication cost and reports state-of-the-art sample and parameter efficien...
-
DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL tasks.
-
HERO: Hierarchical Extrapolation and Refresh for Efficient World Models
HERO accelerates world model inference 1.73x via hierarchical patch-wise refresh in shallow layers and linear extrapolation in deeper layers with minimal quality loss.
-
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
DINO-WM builds world models on pre-trained DINOv2 features to enable zero-shot planning from offline data without rewards or demonstrations.
-
Self-supervised Hierarchical Visual Reasoning with World Model
ResDreamer proposes a residual-reconstruction hierarchical world model for purely self-supervised visual foresight that claims SOTA sample and parameter efficiency in open-world RL.
-
Lifting Embodied World Models for Planning and Control
Composing a policy that maps 2D waypoints to joint actions with a frozen world model yields a lifted world model that achieves 3.8 times lower mean joint error than direct low-level search while being more compute-eff...
-
Simulus: Combining Improvements in Sample-Efficient World Model Agents
Simulus integrates flexible tokenization, intrinsic motivation, prioritized world model replay, and regression-as-classification to achieve state-of-the-art sample efficiency for planning-free world model agents on vi...
-
Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
The work introduces behavior-invariant latent task representations via information-theoretic learning in a Transformer world model plus conservative penalties on imagined rollouts to improve generalization in offline meta-RL.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.