A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Return Decomposition offers a solution by redistributing rewards from observed sequences while preserving policy invariance. While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable return decomposition. In this paper, we start by studying the role of causal generative models in return decomposition by characterizing the generation of Markovian rewards and trajectory-wise long-term return and further propose a framework, called Generative Return Decomposition (GRD), for policy optimization in delayed reward scenarios. Specifically, GRD first identifies the unobservable Markovian rewards and causal relations in the generative process. Then, GRD makes use of the identified causal generative model to form a compact representation to train policy over the most favorable subspace of the state space of the agent. Theoretically, we show that the unobservable Markovian reward function is identifiable, as well as the underlying causal structure and causal models. Experimental results show that our method outperforms state-of-the-art methods and the provided visualization further demonstrates the interpretability of our method.

本文提出了一种基于因果生成模型的回报分解方法，旨在解决强化学习中延迟奖励问题，并演示了该方法在实验中的良好性能及可解释性。

GRD：强化学习中可解释奖励再分配的生成式方法