Multi-Agent Generative Adversarial Imitation Learning
Song, Jiaming, Ren, Hongyu, Sadigh, Dorsa, Ermon, Stefano
–Neural Information Processing Systems
Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-agent imitation learning for general Markov games, where we build upon a generalized notion of inverse reinforcement learning. We further introduce a practical multi-agent actor-critic algorithm with good empirical performance. Our method can be used to imitate complex behaviors in high-dimensional environments with multiple cooperative or competing agents.
Neural Information Processing Systems
Dec-31-2018
- Country:
- Asia > Middle East
- Jordan (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- California > Santa Clara County
- Palo Alto (0.05)
- Illinois > Cook County
- Chicago (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- California > Santa Clara County
- Canada > Quebec
- Asia > Middle East
- Technology: