Research map / Reinforcement learning / Imitation learning
Minimax Optimal Online Imitation Learning via Replay Estimation
Gokul Swamy, Nived Rajaraman, Matt Peng, Sanjiban Choudhury, Drew Bagnell, Steven Wu, Jiantao Jiao, Kannan Ramchandran
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add replay estimation (RE) on top of online moment matching (MM) | MM · PyBullet Walker, 12 expert trajectories | expert-normalized performance | Improved |
| add replay estimation to MM in a noisy-dynamics Walker with i.i.d. noise per timestep | MM · Noisy PyBullet Walker | expert-normalized performance | Improved |
| use the M_MAX membership oracle instead of M_RND or M_VAR (ablation) | RE · PyBullet continuous control | performance and correlation with ideal prefix weights | Improved |
| use RE instead of behavioral cloning under tiny noise in the initial velocity | BC · PyBullet with perturbed initial velocity | expert-normalized performance | Improved |
| fix baseline tuning and implementation bugs after publication | MM and RE · Noisy environments | expert-normalized performance | Mixed |
Closest papers by meaning
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.90)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.90)
- OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning (ICML 2024 · similarity 0.90)
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · similarity 0.90)
- Reward-free World Models for Online Imitation Learning (ICML 2025 · similarity 0.89)
- Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift (NeurIPS 2026 · similarity 0.89)
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.
