AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Large-Scale Retrieval for Reinforcement Learning

Peter Conway Humphreys, Arthur Guez, Olivier Tieleman, Laurent Sifre, Theophane Weber, Timothy P Lillicrap

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 11 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 retrieval of nearest-neighbor expert Go states (vs zeroed neighbors)Retrieval-augmented MuZero-style agent · 9x9 Go test setpolicy top-1 accuracy / value MSEImproved
add retrieval to the agentMCTS agent (200 sims) · Win rate vs Pachiwin rateImproved
retrieve from only 1% of the dataset at evaluation (ablation)Retrieval agent · 9x9 Go test setprediction accuracyHurt
augment retrieval set with ~600k agent-Pachi game states at test time (ablation)Retrieval agent with MCTS · Win rate vs Pachiwin rateImproved
add neighbor randomisation during training (ablation)Retrieval agent policy prior · Win rate vs Pachiwin rateImproved
add neighbor dropout and neighbor regularisation (ablation)Retrieval agent · Win rate vs Pachiwin rateNo clear effect
feed random neighbors at evaluation (vs relevant ones) (ablation)Retrieval agent · Win rate vs Pachiwin rateHurt

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