Evaluating Generalization And Transfer Capacity Of Multi-agent Reinforcement Learning Across Variable Number Of Agents

Abstract

Multi-agent Reinforcement Learning (MARL) problems often require cooperation among agents in order to solve a task. Centralization and decentralization are two approaches used for cooperation in MARL. While fully decentralized methods are prone to converge to suboptimal solutions due to partial observability and nonstationarity, the methods involving centralization suffer from scalability limitations and lazy agent problem. Centralized training decentralized execution paradigm brings out the best of these two approaches; however, centralized training still has an upper limit of scalability not only for acquired coordination performance but also for model size and training time. In this work, we adopt the centralized training with decentralized execution paradigm and investigate the generalization and transfer capacity of the trained models across variable number of agents. This capacity is assessed by training variable number of agents in a specific MARL problem and then performing gre

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyguresti2021evaluating

Related papers

• Transferable Multi-agent Reinforcement Learning With Dynamic Participating Agents (2022)0.00
• Dealing With Non-stationarity In Decentralized Cooperative Multi-agent Deep Reinforcement Learning Via Multi-timescale Learning (2023)0.00
• Adaptability In Multi-agent Reinforcement Learning: A Framework And Unified Review (2025)0.00
• Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00
• An Initial Introduction To Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Mean-field Multi-agent Reinforcement Learning: A Decentralized Network Approach (2021)0.00
• Characterizing Speed Performance Of Multi-agent Reinforcement Learning (2023)4.52
• Multi-agent Reinforcement Learning In Stochastic Networked Systems (2020)0.00