AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

Tian Xu, Zexuan Chen, Zhilong Zhang, Yi-Chen Li, Chenyang Wang, Lei Yuan, Yang Yu

ICML 2026 · Reinforcement learning › Imitation learning · approach: Adversarial imitation learning · 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 reward pretraining (log BC policy as initial reward) on top of BC policy pretraining (ablation)CoPT-AIL · DMControl (8 tasks)convergence speed / returnImproved
add BC policy pretraining alone to AIL (ablation)AIL · DMControl (8 tasks)convergence speed / returnNo clear effect
policy pretraining alone causes instability (ablation)PT-AIL · Cartpole Swingup, Finger Spinstability of learning curvesHurt
co-pretrain policy and reward versus prior AIL methodsCoPT-AIL · DMControl (8 tasks)online interactions to reach near-expert returnImproved

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