Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillation
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/tommyma3/rad
Terminology
Sources
- Longformer: The Long-Document Transformer
- In-Context Reinforcement Learning From Suboptimal Historical Data
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
- Generalized Decision Transformer for Offline Hindsight Information Matching
- In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
- Auto-Encoding Variational Bayes
- In-context Reinforcement Learning with Algorithm Distillation
- Context Cascade Compression: Exploring the Upper Limits of Text Compression
- Decoupled Weight Decay Regularization
- Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
- On First-Order Meta-Learning Algorithms
- Compressive Transformers for Long-Range Sequence Modelling
- A Generalist Agent
- Retrieval-Augmented Decision Transformer: External Memory for In-context RL
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- In-Context Reinforcement Learning for Variable Action Spaces
- Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
- Kimi Linear: An Expressive, Efficient Attention Architecture
- 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