Research map / Reinforcement learning / Imitation learning
SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran
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 |
|---|---|---|---|
| use SafeMIL instead of BC on mixed unlabeled data | offline safe imitation · Walker/Swimmer/Ant-Velocity | normalized cost | Improved |
| use SafeMIL instead of baselines | offline safe imitation · Point-Goal1 | normalized cost | Improved |
| use SafeMIL instead of T-REX | offline safe imitation · Point-Circle2 | normalized cost | Hurt |
| use SafeMIL instead of baselines | offline safe imitation · Point-Button1 | normalized cost | No clear effect |
| increase bag size K from 1 up to 128 (ablation) | SafeMIL · Swimmer-Velocity | normalized cost | Improved |
| use partial trajectories of length H=1, 5, 10 (K=128) instead of full trajectories (ablation) | SafeMIL · Swimmer-Velocity | normalized cost and return | No clear effect |
| weight BC loss per transition instead of per trajectory (ablation) | SafeMIL · Swimmer-Velocity and Point-Goal1 | cost and return | No clear effect |
Closest papers by meaning
- Offline Safe Reinforcement Learning Using Trajectory Classification (AAAI 2025 · similarity 0.90)
- Simplifying Constraint Inference with Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- How to Leverage Diverse Demonstrations in Offline Imitation Learning (ICML 2024 · similarity 0.88)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.88)
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · similarity 0.88)
- SEABO: A Simple Search-Based Method for Offline Imitation Learning (ICLR 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.
