In-Person Poster presentation / top 5% paper
In-context Reinforcement Learning with Algorithm Distillation
Michael Laskin · Luyu Wang · Junhyuk Oh · Emilio Parisotto · Stephen Spencer · Richie Steigerwald · DJ Strouse · Steven Hansen · Angelos Filos · Ethan Brooks · Maxime Gazeau · Himanshu Sahni · Satinder Singh · Volodymyr Mnih
MH1-2-3-4 #96
Keywords: [ transformers ] [ learning to learn ] [ large language models ] [ reinforcement learning ] [ Reinforcement Learning ]
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction problem. A dataset of learning histories is generated by a source RL algorithm, and then a causal transformer is trained by autoregressively predicting actions given their preceding learning histories as context. Unlike sequential policy prediction architectures that distill post-learning or expert sequences, AD is able to improve its policy entirely in-context without updating its network parameters. We demonstrate that AD can reinforcement learn in-context in a variety of environments with sparse rewards, combinatorial task structure, and pixel-based observations, and find that AD learns a more data-efficient RL algorithm than the one that generated the source data.