Research map / Reinforcement learning / MDPs and planning
Provable Representation Learning for Imitation Learning via Bi-level Optimization
Sanjeev Arora, Simon Du, Sham Kakade, Yuping Luo, Nikunj Saunshi
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 |
|---|---|---|---|
| Increase the number of source experts used to learn the representation | Behavioral cloning · NoisyCombinationLock | average return | Improved |
| Increase the number of source experts used to learn the representation | Behavioral cloning · SwimmerVelocity | average return | Improved |
| Use a learned representation from a small number of experts instead of learning the policy from scratch | Behavioral cloning · SwimmerVelocity | average return | Mixed |
| Increase the number of source experts used to learn the representation | Observation-alone imitation learning · NoisyCombinationLock | average return | Improved |
| Increase the number of source experts used to learn the representation | Observation-alone imitation learning · SwimmerVelocity | average return | Improved |
| Use a learned representation from a small number of experts instead of learning the policy from scratch | Observation-alone imitation learning · NoisyCombinationLock and SwimmerVelocity | average return | Mixed |
| Increase the number of source experts used to learn the representation | PPO policy optimization using an imitation-learned representation · NoisyCombinationLock | average return | Mixed |
| Increase the number of source experts used to learn the representation | PPO policy optimization using an imitation-learned representation · SwimmerVelocity | average return | Mixed |
Closest papers by meaning
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · similarity 0.89)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.88)
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation (NeurIPS 2026 · similarity 0.88)
- Robust Visual Imitation Learning with Inverse Dynamics Representations (AAAI 2024 · similarity 0.88)
- Diffusion Model-Augmented Behavioral Cloning (ICML 2024 · similarity 0.88)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.88)
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.
