AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Pierre-Alexandre Kamienny, Jean Tarbouriech, sylvain lamprier, Alessandro Lazaric, Ludovic Denoyer

ICLR 2022 · Reinforcement learning › Visual and representation RL · approach: Unsupervised skill discovery · 0 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 direct-then-diffuse skills composed in a growing tree instead of DIAYN skillsUPSIDE · Bottleneck MazecoverageImproved
Use direct-then-diffuse skills composed in a growing tree instead of DIAYN skillsUPSIDE · Control environmentsstate coverageImproved
Use UPSIDE's learned skill tree for fine-tuning sparse-reward goal reaching instead of DIAYN-20 or TD3UPSIDE · Ant, 48 unknown goalssuccess rateImproved
Use UPSIDE's learned skill tree for fine-tuning sparse-reward goal reaching instead of other methodsUPSIDE · Bottleneck Maze, unknown goalsdiscounted cumulative rewardImproved
Remove tree composition by using flat UPSIDE with tree depth 1 (ablation)UPSIDE · Bottleneck MazeexplorationHurt
Remove tree composition by using flat UPSIDE with tree depth 1 (ablation)UPSIDE · Bottleneck MazecoverageHurt
Keep the diffusing part in flat UPSIDE rather than using DIAYN (ablation)UPSIDE · Coverage environmentscoverageImproved
Remove the direct-then-diffuse structure, scoring the entire directed-skill trajectory as in DIAYN-hier (ablation)UPSIDE · Bottleneck MazeperformanceHurt
Remove the direct-then-diffuse structure, scoring the entire directed-skill trajectory as in DIAYN-hier (ablation)UPSIDE · Evaluated environmentsperformanceHurt
Remove the discriminability-constrained policy-count selection while retaining hierarchical composition and diffusion, as in DIAYN-hier (ablation)UPSIDE · Bottleneck Mazesample efficiency of tree growthHurt
Use SAC rather than TD3 as the policy optimizer (ablation)DIAYN · Bottleneck Mazecoverage: 21.0 (± 0.50) vs 17.67 (± 0.57)No clear effect
Use SAC rather than TD3 as the policy optimizer (ablation)DIAYN · U-mazecoverage: 17.5 (± 0.75) vs 14.67 (± 0.42)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