AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Jonathan Lee, Annie Xie, Aldo Pacchiano, Yash Chandak, Chelsea Finn, Ofir Nachum, Emma Brunskill

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 3 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
use a random in-context dataset instead of dataset-only behavior at test timeDPT · Dark Room, 20 held-out goalsaverage return: 1.1 -> 61.5Improved
pretrain with PPO action labels and PPO in-context datasets (ablation)DPT · Dark RoomreturnNo clear effect
pretrain on random in-context datasets with PPO action labels (ablation)DPT · Dark RoomreturnHurt
reduce pretraining dataset to 10% of its size (ablation)DPT · Dark Room offlinereturn: 10000 samplesHurt
use 8 attention heads (ablation)DPT · Dark Room offlinereturnHurt
vary embedding size, number of layers, attention heads (ablation)DPT · Dark Room offlinereturnNo clear effect
mix expert data into the pretraining datasets (ablation)DPT-Exp · Bandits with varying expert fractionsuboptimalityMixed
change test reward distribution from Gaussian to BernoulliDPT · Bernoulli banditsregretNo 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