AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

CUP: Critic-Guided Policy Reuse

Jin Zhang, Siyuan Li, Chongjie Zhang

NeurIPS 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Stabilizing deep actor-critic · 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 CUP’s critic-guided source-policy selection and adaptive imitation regularization instead of SAC aloneSAC · Meta-World: Hammer, Peg-Insert-Side, Push-Wall, Pick-Place-Wall, Push-Back, Shelf-Placecumulative returnImproved
Use CUP instead of HAAR, PTF, MULTIPOLAR, or MAMBA for policy reuseMeta-World policy reuse · Meta-World target taskscumulative returnImproved
Add up to 3 random source policies (ablation)CUP · Meta-World target taskscumulative returnNo clear effect
Add 4 or 5 random source policies (ablation)CUP · Meta-World target taskscumulative returnHurt
Use 3 random source policies with no useful source policy (ablation)CUP · Meta-World transfer with useless sourcessample efficiencyNo clear effect
Add Reach as a useful source policy alongside 3 random policies (ablation)CUP · Meta-World transfer with 3 Random Sources+Reachlearning performanceImproved
Increase the source-policy set from 3 to 6 policies (ablation)CUP · Meta-World, especially Pick-Place-Wall and Peg-Insert-SideperformanceImproved
Increase the source-policy set from 3 to 6 policies (ablation)MULTIPOLAR · Meta-World target tasksperformanceHurt
Vary CUP’s additional regularization hyperparameters (ablation)CUP · Meta-World target tasksperformanceNo clear effect
Use a source-policy set containing only unrelated or less-related policies (ablation)CUP · Bin-Picking and Stick-Pullperformance improvement over SACMixed

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