Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-Agent Generative Adversarial Imitation Learning

About

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.

Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon• 2018

Related benchmarks

TaskDatasetResultRank
Road CrossingThree-Agent Road Crossing
Collision Rate (per 100 Steps)32
16
Multi-agent NavigationTwo-Agent Swap 100 sampled trajectories
Agent-Agent Collisions97
4
Trajectory Distribution MatchingTwo-Agent Swap Robosuite simulation (100 sampled trajectories)
EMD (Agent 1)4.67
4
Trajectory Distribution MatchingThree-Agent Road Crossing
EMD (Agent 1)1.2749
4
Two-Arm LiftTwo-Arm Lift Simulation
Successful Lifts0.00e+0
4
Showing 5 of 5 rows

Other info

Follow for update