MAAIGTLGMay 27, 2023

Reinforcement Learning With Reward Machines in Stochastic Games

arXiv:2305.17372v3
Originality Incremental advance
AI Analysis

This addresses complex task learning in multi-agent systems, offering a novel method for handling non-Markovian rewards, though it is incremental as it builds on existing reward machine and Q-learning frameworks.

The paper tackles multi-agent reinforcement learning in stochastic games with non-Markovian rewards by developing QRM-SG, an algorithm that integrates reward machines to learn best-response strategies at Nash equilibrium, achieving convergence in 7500, 1000, and 1500 episodes across three case studies where baselines failed.

We investigate multi-agent reinforcement learning for stochastic games with complex tasks, where the reward functions are non-Markovian. We utilize reward machines to incorporate high-level knowledge of complex tasks. We develop an algorithm called Q-learning with reward machines for stochastic games (QRM-SG), to learn the best-response strategy at Nash equilibrium for each agent. In QRM-SG, we define the Q-function at a Nash equilibrium in augmented state space. The augmented state space integrates the state of the stochastic game and the state of reward machines. Each agent learns the Q-functions of all agents in the system. We prove that Q-functions learned in QRM-SG converge to the Q-functions at a Nash equilibrium if the stage game at each time step during learning has a global optimum point or a saddle point, and the agents update Q-functions based on the best-response strategy at this point. We use the Lemke-Howson method to derive the best-response strategy given current Q-functions. The three case studies show that QRM-SG can learn the best-response strategies effectively. QRM-SG learns the best-response strategies after around 7500 episodes in Case Study I, 1000 episodes in Case Study II, and 1500 episodes in Case Study III, while baseline methods such as Nash Q-learning and MADDPG fail to converge to the Nash equilibrium in all three case studies.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes