Y Wang, A Sinha, S CH-Wang, and MP Wellman
20th IEEE International Conference on Machine Learning and Applications (ICMLA), December 2021 (forthcoming).
In many policy-learning applications, the agent may execute a set of actions at each decision stage. Choosing among an exponential number of alternatives poses a computational challenge, and even representing actions naturally expressed as sets can be a tricky design problem. Building upon prior approaches that employ deep neural networks and iterative construction of action sets, we introduce a reward-shaping approach to apportion reward to each atomic action based on its marginal contribution within an action set, thereby providing useful feedback for learning to build these sets. We demonstrate our method in two environments where action spaces are combinatorial. Experiments reveal that our method significantly accelerates and stabilizes policy learning with combinatorial actions.