Distributional Reward Decomposition for Reinforcement Learning
This addresses a specific challenge in RL for tasks with multiple reward channels, offering an incremental improvement over prior decomposition methods.
The paper tackles the problem of reward decomposition in reinforcement learning for environments with multiple reward channels, proposing DRDRL to capture this structure without prior knowledge, resulting in better performance than existing methods.
Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward channel. In those environments the full reward can be decomposed into sub-rewards obtained from different channels. Existing work on reward decomposition either requires prior knowledge of the environment to decompose the full reward, or decomposes reward without prior knowledge but with degraded performance. In this paper, we propose Distributional Reward Decomposition for Reinforcement Learning (DRDRL), a novel reward decomposition algorithm which captures the multiple reward channel structure under distributional setting. Empirically, our method captures the multi-channel structure and discovers meaningful reward decomposition, without any requirements on prior knowledge. Consequently, our agent achieves better performance than existing methods on environments with multiple reward channels.