AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

In-context Reinforcement Learning with Algorithm Distillation

Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Stenberg Hansen, Angelos Filos, Ethan Brooks, maxime gazeau, Himanshu Sahni and 2 more

ICLR 2023 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add across-episode causal transformer distillation of source RL learning histories (AD) vs expert-only data (ED)AD · Dark Room, Dark Room Hard, Dark Key-to-Door, WatermazereturnImproved
Train on expert trajectories only (Expert Distillation) instead of learning histories (ablation)ED · Dark Room, Dark Room Hard, WatermazereturnHurt
Distill from multi-stream learning histories into single-stream AD (data-efficiency vs source)AD · Dark environments and Watermazesample efficiency vs source algorithmImproved
Increase across-episode context length to 2-4 episodes (ablation)AD · Dark RoomreturnImproved
Replace transformer with LSTM in AD (ablation)AD · Dark Key-to-DoorreturnHurt
Add label smoothing (alpha 0.2) to AD (ablation)AD · Dark Room (Hard)in-context learning performanceImproved
Pre-fill context with demonstration policy dataAD · Dark RoomreturnImproved
Pre-fill context with demonstration policy dataED · Dark RoomreturnNo clear effect
Use RL2 (online meta-RL) as upper bound referenceRL2 · Dark Room, WatermazereturnNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy