AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Explore to Generalize in Zero-Shot RL

Ev Zisselman, Itai Lavie, Daniel Soudry, Aviv Tamar

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 1 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 trained max-entropy exploration policy when the reward-policy ensemble disagrees, rather than random actions (ablation)ExpGen · Mazetest score: 6.2 ± 0.2 -> 8.2 ± 0.1Improved
Increase ensemble size from 4 to 10 (ablation)ExpGen · Mazetest score: 8.02±0.06 -> 8.22±0.11Improved
Use L0 rather than L2 state similarity (ablation)ExpGen · Mazetest score: 8.3 ± 0.2 -> 8.2 ± 0.1No clear effect
Use L0 rather than L2 state similarity (ablation)ExpGen · Heisttest score: 7.4 ± 0.2 -> 7.4 ± 0.1No clear effect
Combine intrinsic exploration reward with extrinsic reward in one weighted reward instead of using ExpGen's ensemble switching (ablation)PPO on Maze · Mazetest scoreHurt
Add a GRU memory unit to the max-entropy policy (ablation)Max-entropy policy · Maze, Jumper, and Minermax-entropy performanceImproved
Add a GRU to an extrinsic-reward policy (ablation)PPO · Maze and Jumper with 200 training levelsextrinsic-reward performanceHurt
Train for maximum-entropy exploration rather than extrinsic rewardPolicy trained on ProcGen · Maze, Jumper, and Miner with 200 training levelsgeneralization gap: 1.7% vs 38.8%; 8.5% vs 27.5%; 4.3% vs 13.1%Improved
Combine ExpGen with IDAAC rather than using IDAAC aloneIDAAC · ProcGen test suiteaggregate performance: 0.6Improved

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