Multi-Agent Generative Adversarial Imitation Learning
Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon
–Neural Information Processing Systems
If the reward function does not cover all important aspects of the task, the agent could easily learn undesirable behaviors [4].
Neural Information Processing Systems
Feb-12-2026, 10:47:50 GMT
- Country:
- North America
- United States
- Illinois > Cook County
- Chicago (0.04)
- California > Santa Clara County
- Palo Alto (0.05)
- Illinois > Cook County
- Canada > Quebec
- Montreal (0.04)
- United States
- Asia > Middle East
- Jordan (0.04)
- North America
- Technology: