In-Context Reinforcement Learning via Communicative World Models

arXiv:2508.06659 · cs.LG, cs.AI · Submitted 2025-08-08 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-08-08

Updated: 2026-06-07

Code: https://github.com/fernando-ml/CORAL

Terminology

• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Control Agent — 1× in this paper
• Information Agent — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes

Sources

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• D4RL: Datasets for Deep Data-Driven Reinforcement Learning
• Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
• A Survey of In-Context Reinforcement Learning
• NAVIX: Scaling MiniGrid Environments with JAX
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Proximal Policy Optimization Algorithms
• Learning to reinforcement learn

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks