AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Adversarial Dual On-Policy Distillation from Expressive Teacher

Zhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor Tsang, Yang You

ICML 2026 · Reinforcement learning › Imitation learning · approach: Imitation combined with 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
add FA-OPD online distillation to flow/diffusion behavioral cloning (expert return 1965.58)Flow-Matching Policy · Walker2d sub-optimal expert ID 2average return: 1342.47 -> 2093.14Improved
add FA-OPD online distillation with near-novice expert (return 265.36)Diffusion Policy · Walker2d sub-optimal expert ID 1average return: 247.24 -> 99.05Hurt
add FA-OPD online distillation with strong expert (return 5357.37)Diffusion Policy · Walker2d sub-optimal expert ID 5average return: 2091.17 -> 4287.24Improved
add online interaction to DP/FP under 1.5x noiseFlow-Matching Policy · Hand-rotate noise generalizationsuccess rate: 0.91 to nearly 0.82 (DP/FP) vs above 0.95 (FA-OPD)Improved
student distilled from FM teacher instead of updating FM policy online with PPOFM-PPO · Maze2dsuccess rate: peak near 0.33 then declinesImproved
add action-distillation channel to reward-only distillation (beta>0) (ablation)FA-OPD · ablation over betaperformanceImproved

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