AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Offline Reinforcement Learning with Value-based Episodic Memory

Xiaoteng Ma, Yiqin Yang, Hao Hu, Jun Yang, Chongjie Zhang, Qianchuan Zhao, Bin Liang, Qihan Liu

ICLR 2022 · Reinforcement learning › Offline RL · approach: Simple practical offline RL · 10 citations (OpenAlex)

Read the paper

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 VEM rather than the strongest reported baselineOffline RL · AntMaze tasksnormalized scoreImproved
Use VEM rather than the strongest reported baselineOffline RL · Adroit tasksnormalized scoreMixed
Use VEM rather than the strongest reported baselineOffline RL · MuJoCo tasksnormalized scoreMixed
Replace EVL with BCQ value learning (ablation)VEM · Adroit-human tasksnormalized scoreHurt
Replace episodic memory planning with standard n-step value estimation (ablation)VEM · AntMaze tasksconvergence speedHurt
Replace expectile loss with quantile loss (ablation)VEM · Adroit tasksstabilityHurt
Increase expectile fraction too far (for example, tau=0.9) (ablation)VEM · Adroit pen-humanperformanceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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