AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Curriculum Reinforcement Learning via Constrained Optimal Transport

Pascal Klink, Haoyi Yang, Carlo D’Eramo, Jan Peters, Joni Pajarinen

ICML 2022 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL

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
Generate curriculum via constrained Wasserstein optimal transport (CURROT) instead of KL-based interpolation (SPRL)Curriculum RL · Sparse goal reachingSuccess rate on feasible subspaceImproved
Use Wasserstein-based curriculum instead of Gaussian-restricted SPRLPoint mass environment · Point mass (bi-modal target)Curriculum coverage of target gatesImproved
Use CURROT instead of baselines on bipedal walker stump tracksCurriculum RL · Bipedal Walker Stump Tracks (mostly infeasible and mostly trivial)Final performance (% mastered tasks)Mixed

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