Difference Rewards Policy Gradients
This work addresses the critical problem of multi-agent credit assignment for researchers and practitioners developing multi-agent reinforcement learning systems, offering an alternative to Q-function learning methods.
This paper introduces Dr.Reinforce, a novel algorithm that combines difference rewards with policy gradients to address multi-agent credit assignment in multi-agent reinforcement learning. It enables learning decentralized policies when the reward function is known, and a version is proposed for unknown reward functions using a learned reward network.
Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing an agent's contribution to the overall performance, which is crucial for learning good policies. We propose a novel algorithm called Dr.Reinforce that explicitly tackles this by combining difference rewards with policy gradients to allow for learning decentralized policies when the reward function is known. By differencing the reward function directly, Dr.Reinforce avoids difficulties associated with learning the Q-function as done by Counterfactual Multiagent Policy Gradients (COMA), a state-of-the-art difference rewards method. For applications where the reward function is unknown, we show the effectiveness of a version of Dr.Reinforce that learns an additional reward network that is used to estimate the difference rewards.