Adjust Planning Strategies to Accommodate Reinforcement Learning Agents
This work addresses a specific challenge in agent control for AI systems, but it appears incremental as it builds on existing methods for combining reinforcement learning and planning.
The paper tackles the problem of integrating reinforcement learning and planning by optimizing planning parameters to define their functional boundary, resulting in a non-gradient method that accelerates optimization and leverages agent reaction capabilities.
In agent control issues, the idea of combining reinforcement learning and planning has attracted much attention. Two methods focus on micro and macro action respectively. Their advantages would show together if there is a good cooperation between them. An essential for the cooperation is to find an appropriate boundary, assigning different functions to each method. Such boundary could be represented by parameters in a planning algorithm. In this paper, we create an optimization strategy for planning parameters, through analysis to the connection of reaction and planning; we also create a non-gradient method for accelerating the optimization. The whole algorithm can find a satisfactory setting of planning parameters, making full use of reaction capability of specific agents.