AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Self-Paced Deep Reinforcement Learning

Pascal Klink, Carlo D'Eramo, Jan R Peters, Joni K. Pajarinen

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 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 SPDL curriculum generation instead of Default learningPPO · Point Mass P3Daverage final reward: 9.35\pm0.1 vs 2.46\pm0.0Improved
Use SPDL curriculum generation instead of ALP-GMMPPO · Point Mass P2Daverage final reward: 9.02 \pm 0.4 vs 5.24\pm0.4Improved
Use SPDL curriculum generation instead of Default learningPPO · AntrewardImproved
Use ALP-GMM curriculum generation instead of Default learningPPO · AntrewardNo clear effect
Use a curriculum rather than sample directly from the target distributionBall-Catching agents · Ball-CatchingrewardImproved
Initialize the SPDL context distribution (ablation)Ball-Catching agents · Ball-Catchingaverage final reward: 47.0\pm2.0 vs 43.3\pm2.0; 53.9\pm0.4 vs 49.3\pm1.4No clear effect
Use SPDL rather than the other evaluated curriculaTRPO and PPO · Ball-Catchingaverage final rewardNo 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