AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments

Sang-Hyun Lee, Seung-Woo Seo

ICML 2023 · Reinforcement learning › Visual and representation RL · approach: Unsupervised skill discovery

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
Incremental skill discovery with state-coverage-expanding objective and skill evaluation (full method) vs. prior unsupervised skill discovery baselinesskills for changing environments · maze2d-medium-v1 downstreamaverage return (100 episodes): 286.15 vs 127.67 (DISk), 22.63 (DADS), 7.96 (DIAYN)Improved
Incremental skill discovery with state-coverage-expanding objective and skill evaluation (full method) vs. prior baselinesskills for changing environments · HalfCheetah-hurdle-tunnel-sequence-v3 downstreamaverage return (100 episodes): 608.69 vs 88.99 (DISk), 70.53 (DADS), 69.03 (DIAYN)Improved
Incremental skill discovery with state-coverage-expanding objective and skill evaluation (full method) vs. prior baselinesskills for changing environments · HalfCheetah-tunnel-hurdle-sequence-v3 downstreamaverage return (100 episodes): 619.38 vs 304.47 (DISk), 237.90 (DADS), 63.83 (DIAYN)Improved
Retaining previously learned skills (DISk) vs. not retaining (DIAYN/DADS) on maze downstreamDISk baseline · maze2d-medium-v1 downstreamaverage return (100 episodes): 127.67 vs 22.63 (DADS), 7.96 (DIAYN)Improved
Skill evaluation process (similarity and entropy criteria) added to skill discovery (ablation)skill set in HalfCheetah-continual-v3 · HalfCheetah-continual-v3 skill compositionstate coverage (qualitative)No clear effect
Skill evaluation process added to skill discovery in Ant-v3 stationary setting (ablation)skill set in Ant-v3 · Ant-v3 skill diversity (qualitative)behavior diversity (qualitative)No 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