Quantifying Agent Interaction In Multi-agent Reinforcement Learning For Cost-efficient Generalization
2023 · Yuxin Chen, Chen Tang, Ran Tian, et al.
Abstract
Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination of this relationship sheds light on effectively training agents for diverse scenarios. In this study, we present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment. We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performance of the ego agent; however, this improvement varies across distinct scenarios and environments. LoI proves effective in predicting these improvement disparities within specific scenarios. Furthermore, we introduce a LoI-guided resource allocation method tailored to train a set of policies for diverse scenarios under a constrained budget. Our results demonstrate that strategic resource allocatio
Authors
(none)
Tags
Stats
Related papers
- Quantifying The Effects Of Environment And Population Diversity In Multi-agent Reinforcement Learning (2021)9.03
- Locality Matters: A Scalable Value Decomposition Approach For Cooperative Multi-agent Reinforcement Learning (2021)0.00
- High-order Interactions Modeling For Interpretable Multi-agent Q-learning (2025)0.00
- Evaluating Generalization And Transfer Capacity Of Multi-agent Reinforcement Learning Across Variable Number Of Agents (2021)0.00
- Efficiently Quantifying Individual Agent Importance In Cooperative MARL (2023)0.00
- Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
- Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00
- Mitigating Relative Over-generalization In Multi-agent Reinforcement Learning (2024)0.00