Research map / Reinforcement learning / Imitation learning
Imitation Learning from Imperfect Demonstration
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 confidence and unlabeled demonstrations with 2IWIL or IC-GAIL instead of the baseline methods | Imitation learning on Mujoco tasks · Mujoco tasks | average return | Helped |
| Add confidence-based reweighting | GAIL · Mujoco tasks | average return | Helped |
| Use more unlabeled demonstrations | 2IWIL and IC-GAIL · Mujoco tasks | average return | Helped |
| Add Gaussian noise to confidence scores | 2IWIL and IC-GAIL · Ant-v2 | average return | No clear effect |
| Use IC-GAIL instead of 2IWIL | Imitation learning · Mujoco tasks | convergence speed | Hurt |
Closest papers by meaning
- PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations (ICLR 2025 · similarity 0.92)
- Learning to Weight Imperfect Demonstrations (ICML 2021 · similarity 0.92)
- Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality (NeurIPS 2021 · similarity 0.91)
- Imitation Learning from Purified Demonstrations (ICML 2024 · similarity 0.89)
- Limited Preference Aided Imitation Learning from Imperfect Demonstrations (ICML 2024 · similarity 0.88)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (AAAI 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.