Research map / Reinforcement learning / Imitation learning
Generative Adversarial Imitation Learning
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 |
|---|---|---|---|
| Adding GAIL (adversarial occupancy-measure matching) instead of baselines | imitation learning on MuJoCo tasks · HalfCheetah, Walker, Ant, Humanoid (multiple dataset sizes) | return | Helped |
| Causal entropy regularization lambda=1e-3 added to GAIL (ablation) | GAIL on Reacher · Reacher, 4 trajectories | return | Mixed |
| Causal entropy regularization lambda=1e-2 added to GAIL (ablation) | GAIL on Reacher · Reacher, 18 trajectories | return | No clear effect |
| Behavioral cloning versus GAIL on Reacher | Reacher · Reacher, 4 trajectories | return | Hurt |
Closest papers by meaning
- Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation (ICML 2019 · similarity 0.93)
- Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation (ICML 2022 · similarity 0.92)
- Diffusion Imitation from Observation (NeurIPS 2024 · similarity 0.90)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (AAAI 2024 · similarity 0.90)
- Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment (NeurIPS 2024 · similarity 0.89)
- Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching (ICLR 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.