Research map / Reinforcement learning / Imitation learning
Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
Antoine Moulin, Gergely Neu, Luca Viano
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies offline imitation learning in MDPs using only Q^pi-realizability of a comparison class rather than expert-policy realizability.
Problem
Offline imitation learning from expert state-action pairs in MDPs, where prior work assumes the expert policy lies in a known tractable policy class; this paper drops that assumption.
Approach
Replaces expert-policy realizability with Q^pi-realizability (the value functions of policies in a class are representable), leveraging this alternative structure to learn well-performing policies from expert state-action data.
Closest papers by meaning
- Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage (NeurIPS 2021 · similarity 0.91)
- Toward the Fundamental Limits of Imitation Learning (NeurIPS 2020 · similarity 0.91)
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback (NeurIPS 2026 · similarity 0.90)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.90)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.90)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · 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.
