Research map / Reinforcement learning / Imitation learning
Expert Data Augmentation in Imitation Learning (Student Abstract)
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 |
|---|---|---|---|
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · MsPacman | return: 207.6±4.8 -> 1061.2±177.2 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · Breakout | return: 0.9±0.8 -> 17.0±9.1 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · SpaceInvaders | return: 175±58.5 -> 218.6±100.7 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · Qbert | return: 0±0 -> 770.5±350.4 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · Hopper | return: 94.9±28.9 -> 1722.4±278.7 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · Ant | return: 521.8±157.1 -> 931.8±477.6 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · Walker2d | return: 165.9±43.3 -> 422.3±319.6 | Helped |
| Augment one expert trajectory with sampled transitions that return to expert-like states | BC · HalfCheetah | return: -174.3±464.1 -> 43.7±102.9 | Helped |
Closest papers by meaning
- How to Leverage Diverse Demonstrations in Offline Imitation Learning (ICML 2024 · similarity 0.89)
- Diffusion Model-Augmented Behavioral Cloning (ICML 2024 · similarity 0.89)
- A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search (NeurIPS 2025 · similarity 0.89)
- 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)
- Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction (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.