Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning
This addresses the agent-temporal credit assignment problem for multi-agent systems in sparse reward environments, though it appears incremental as it builds on reward shaping techniques.
The paper tackles the problem of sparse or delayed global rewards in multi-agent reinforcement learning by introducing Temporal-Agent Reward Redistribution (TAR^2), which redistributes rewards temporally and across agents to stabilize and accelerate learning, with empirical results showing it performs as well as or better than traditional methods.
In multi-agent environments, agents often struggle to learn optimal policies due to sparse or delayed global rewards, particularly in long-horizon tasks where it is challenging to evaluate actions at intermediate time steps. We introduce Temporal-Agent Reward Redistribution (TAR$^2$), a novel approach designed to address the agent-temporal credit assignment problem by redistributing sparse rewards both temporally and across agents. TAR$^2$ decomposes sparse global rewards into time-step-specific rewards and calculates agent-specific contributions to these rewards. We theoretically prove that TAR$^2$ is equivalent to potential-based reward shaping, ensuring that the optimal policy remains unchanged. Empirical results demonstrate that TAR$^2$ stabilizes and accelerates the learning process. Additionally, we show that when TAR$^2$ is integrated with single-agent reinforcement learning algorithms, it performs as well as or better than traditional multi-agent reinforcement learning methods.