Research map / Reinforcement learning / Imitation learning
Model-Free Imitation Learning with Policy Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use IM-REINFORCE rather than LPAL for apprenticeship learning | Apprenticeship learning on 64 × 64 gridworlds · Gridworld | Performance relative to LPAL: at least 98% | Mixed |
| Use IM-REINFORCE rather than LPAL | Apprenticeship learning · Gridworld with 65536 states | Training time: 10 minutes -> 4 minutes | Helped |
| Use model-free IM-TRPO instead of model-based CIOC | Imitation learning in planar navigation · Objectworld | Excess cost | No clear effect |
| Use IM-TRPO instead of IM-REINFORCE | Imitation learning with linear costs · Waterworld, varying observation dimensions | Excess cost | Helped |
| Use IM-TRPO with 610-dimensional partial observations | Highway driving imitation · Highway driving | Behavioral similarity | Mixed |
Closest papers by meaning
- Reward-free World Models for Online Imitation Learning (ICML 2025 · similarity 0.92)
- Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model (ICLR 2025 · similarity 0.91)
- Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift (NeurIPS 2026 · similarity 0.89)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.89)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.89)
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · 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.