Research map / Reinforcement learning / Imitation learning
Exponentially Weighted Imitation Learning for Batched Historical Data
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 |
|---|---|---|---|
| add exponential advantage weighting (beta=1.0) to imitation learning (ablation) | MARWIL · TORCS | sum of rewards per episode: 2710 -> 9492 | Helped |
| MARWIL instead of PG at beta=1.0 | offline policy learning · TORCS | sum of rewards per episode: 7152 -> 9492 | Helped |
| MARWIL instead of PG at beta=0.25 | offline policy learning · TORCS | sum of rewards per episode: 6396 -> 5583 | Hurt |
| increase beta from 0.25 to 1.0 (ablation) | MARWIL · TORCS | sum of rewards per episode: 5583 -> 9492 | Helped |
Closest papers by meaning
- Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning (ICLR 2025 · similarity 0.88)
- BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning (NeurIPS 2020 · similarity 0.88)
- Learning Self-Imitating Diverse Policies (ICLR 2019 · similarity 0.87)
- Planning for Sample Efficient Imitation Learning (NeurIPS 2022 · similarity 0.87)
- Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning (ICML 2025 · similarity 0.86)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.86)
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.