Analysing Factorizations Of Action-value Networks For Cooperative Multi-agent Reinforcement Learning

Abstract

Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in [4] and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keycastellini2019analysing

Related papers

• Towards Understanding Cooperative Multi-agent Q-learning With Value Factorization (2020)0.00
• Impact Of Relational Networks In Multi-agent Learning: A Value-based Factorization View (2023)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Concaveq: Non-monotonic Value Function Factorization Via Concave Representations In Deep Multi-agent Reinforcement Learning (2023)5.84
• Residual Q-networks For Value Function Factorizing In Multi-agent Reinforcement Learning (2022)10.21
• Local Advantage Networks For Cooperative Multi-agent Reinforcement Learning (2021)0.00
• A Unified Framework For Factorizing Distributional Value Functions For Multi-agent Reinforcement Learning (2023)0.00