Yaodong Yang

TL;DR: In this paper, a mean field Q-learning and mean field Actor-Critic algorithms are proposed to solve the Ising model via model-free reinforcement learning methods. But the authors admit that the learning of the individual agent's optimal policy depends on the dynamics of the population, while the dynamics change according to the collective patterns of individual policies.

TL;DR: This paper introduces a Multiagent Bidirectionally-Coordinated Network (BiCNet) with a vectorised extension of actor-critic formulation and demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of advanced coordination strategies that have been commonly used by experienced game players.

TL;DR: This analysis demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of coordination strategies that is similar to these of experienced game players, and is easily adaptable to the tasks with heterogeneous agents.

TL;DR: This paper addresses the order dispatching problem using multi-agent reinforcement learning (MARL), which follows the distributed nature of the peer-to-peer ridesharing problem and possesses the ability to capture the stochastic demand-supply dynamics in large-scale ridesh sharing scenarios.

Abstract: Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse of the dimensionality and the exponential growth of agent interactions. In this paper, we present Mean Field Reinforcement Learning where the interactions within the population of agents are approximated by those between a single agent and the average effect from the overall population or neighboring agents; the interplay between the two entities is mutually reinforced: the learning of the individual agent’s optimal policy depends on the dynamics of the population, while the dynamics of the population change according to the collective patterns of the individual policies. We develop practical mean field Q-learning and mean field Actor-Critic algorithms and analyze the convergence of the solution to Nash equilibrium. Experiments on Gaussian squeeze, Ising model, and battle games justify the learning effectiveness of our mean field approaches. In addition, we report the first result to solve the Ising model via model-free reinforcement learning methods.