Hierarchical Modular Reinforcement Learning Method and Knowledge Acquisition of State-Action Rule for Multi-target Problem
This work addresses multi-target decision-making in reinforcement learning, but it appears incremental as it builds on existing HMRL with minor extensions.
The paper tackles the multi-target problem in reinforcement learning by extending Hierarchical Modular Reinforcement Learning (HMRL) with an 'AT field' function that considers distances between targets and agent advantages, and extracts state-action rules using C4.5. Experimental results demonstrate the method's effectiveness, though no specific numerical gains are provided.
Hierarchical Modular Reinforcement Learning (HMRL), consists of 2 layered learning where Profit Sharing works to plan a prey position in the higher layer and Q-learning method trains the state-actions to the target in the lower layer. In this paper, we expanded HMRL to multi-target problem to take the distance between targets to the consideration. The function, called `AT field', can estimate the interests for an agent according to the distance between 2 agents and the advantage/disadvantage of the other agent. Moreover, the knowledge related to state-action rules is extracted by C4.5. The action under the situation is decided by using the acquired knowledge. To verify the effectiveness of proposed method, some experimental results are reported.