Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning
This addresses exploration challenges in cooperative multi-agent systems, offering a novel method for improving performance in benchmarks, though it is incremental as it builds on existing value decomposition frameworks.
The paper tackles the problem of efficient exploration in cooperative deep multi-agent reinforcement learning by proposing Conditionally Optimistic Exploration (COE), which uses an action-conditioned optimistic bonus based on sequential agent dependencies, and experiments show it outperforms state-of-the-art exploration methods on hard-exploration tasks.
Efficient exploration is critical in cooperative deep Multi-Agent Reinforcement Learning (MARL). In this work, we propose an exploration method that effectively encourages cooperative exploration based on the idea of sequential action-computation scheme. The high-level intuition is that to perform optimism-based exploration, agents would explore cooperative strategies if each agent's optimism estimate captures a structured dependency relationship with other agents. Assuming agents compute actions following a sequential order at \textit{each environment timestep}, we provide a perspective to view MARL as tree search iterations by considering agents as nodes at different depths of the search tree. Inspired by the theoretically justified tree search algorithm UCT (Upper Confidence bounds applied to Trees), we develop a method called Conditionally Optimistic Exploration (COE). COE augments each agent's state-action value estimate with an action-conditioned optimistic bonus derived from the visitation count of the global state and joint actions of preceding agents. COE is performed during training and disabled at deployment, making it compatible with any value decomposition method for centralized training with decentralized execution. Experiments across various cooperative MARL benchmarks show that COE outperforms current state-of-the-art exploration methods on hard-exploration tasks.