Research map / Reinforcement learning / Imitation learning
On Computation and Generalization of 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 |
|---|---|---|---|
| Use greedy stochastic gradient updates for the reward instead of alternating mini-batch updates | GAIL · Acrobot, MountainCar, and Hopper | average reward | No clear effect |
| Use a neural network reward instead of a kernel reward | GAIL · Acrobot, MountainCar, and Hopper | average reward | Helped |
| Use a neural network reward instead of a kernel reward | GAIL · Acrobot, MountainCar, and Hopper | training stability and convergence time | Hurt |
Closest papers by meaning
- Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate (ICML 2020 · similarity 0.96)
- C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory (NeurIPS 2024 · similarity 0.96)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (AAAI 2024 · similarity 0.95)
- Diffusion-Reward Adversarial Imitation Learning (NeurIPS 2024 · similarity 0.92)
- Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation (NeurIPS 2024 · similarity 0.90)
- Improving Reward Model Generalization from Adversarial Process Enhanced Preferences (ICML 2025 · 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.