Emergence Of In-context Reinforcement Learning From Noise Distillation

Abstract

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for data, which needs to be generated by RL agents or labeled with actions from an optimal policy. In order to address this prevalent problem, we propose AD\(^\epsilon\), a new data acquisition approach that enables in-context Reinforcement Learning from noise-induced curriculum. We show that it is viable to construct a synthetic noise injection curriculum which helps to obtain learning histories. Moreover, we experimentally demonstrate that it is possible to alleviate the need for generation using optimal policies, with in-context RL still able to outperform the best suboptimal policy in a learning dataset by a 2x margin.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzisman2023emergence

Related papers

• Generalization In Reinforcement Learning With Selective Noise Injection And Information Bottleneck (2019)0.00
• Regret-based Defense In Adversarial Reinforcement Learning (2023)0.00
• Transformers Can Learn Temporal Difference Methods For In-context Reinforcement Learning (2024)0.00
• Contextual Intelligence The Next Leap For Reinforcement Learning (2026)0.00
• Prend: Enhancing Intrinsic Motivation In Reinforcement Learning Through Pre-trained Network Distillation (2024)0.00
• Online Reinforcement Learning In Non-stationary Context-driven Environments (2023)0.00
• Reinforcement Learning In Presence Of Discrete Markovian Context Evolution (2022)0.00
• Exploring Parity Challenges In Reinforcement Learning Through Curriculum Learning With Noisy Labels (2023)2.26