2026-05-22T05:11:53Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-1930022024-12-23T18:01:48Zoai_pmh:repo_items

193002 https://hdl.handle.net/2286/R.2.N.193002 http://rightsstatements.org/vocab/InC/1.0/ All Rights Reserved 2024 2026-05-01T09:24:11 50 pages Masters Thesis Academic theses Text eng Kim, Hyohun Xu, Zhe ZX Lee, Hyunglae HL Berman, Spring SB Arizona State University Partial requirement for: M.S., Arizona State University, 2024 Field of study: Engineering Multi-agent reinforcement learning (MARL) plays a pivotal role in artificial intelligence by facilitating the learning process in complex environments inhabited by multiple entities. This thesis explores the integration of learning high-level knowledge through reward machines (RMs) with MARL to effectively manage non-Markovian reward functions in non-cooperative stochastic games. Reward machines offer a sophisticated way to model the temporal structure of rewards, thereby providing an enhanced representation of agent decision-making processes. A novel algorithm JIRP-SG is introduced, enabling agents to concurrently learn RMs and optimize their best response policies while navigating the intricate temporal dependencies present in non-cooperative settings. This approach employs automata learning to iteratively acquire RMs and utilizes the Lemke-Howson method to update the Q-functions, aiming for a Nash equilibrium. It is demonstrated that the method introduced reliably converges to accurately encode the reward functions and achieve the optimal best response policy for each agent over time. The effectiveness of the proposed approach is validated through case studies, including a Pacman Game scenario and a Factory Assembly scenario, illustrating its superior performance compared to baseline methods. Additionally, the impact of batch size on learning performance is examined, revealing that a diligent agent employing smaller batches can surpass the performance of an agent using larger batches, which fails to summarize experiences as effectively. Artificial Intelligence Robotics Artificial Intelligence Reinforcement Learning Reward Machine Joint Learning of Reward Machines and Policies for Multi-Agent Reinforcement Learning in Non-Cooperative Stochastic Games