Multi-Agent Reinforcement Learning for Multi-Object Tracking

We present a novel, multi-agent reinforcement learning formulation of multi-object tracking that treats creating, propagating, and terminating object tracks as actions in a sequential decision-making problem. In our formulation, each agent tracks a single object at a time by updating a Bayesian filter according to a discrete set of actions. At each timestep, the reward received is dependent on the joint actions taken by all agents and the ground truth object tracks. We optimize for different tracking metrics directly while propagating covariance information about each object's state. We use trust region policy optimization (TRPO) to train a shared policy across all agents, parameterized by a multi-layer neural network. Our experiments show an improvement in tracking accuracy over similar state-of-the-art, rule-based approaches on a popular multi-object tracking dataset.