Temporal-Differential Learning in Continuous Environments
This addresses the challenge of developing RL techniques for continuous environments, though it appears incremental as it builds on traditional temporal-difference learning.
The paper tackles the problem of reinforcement learning in continuous environments by introducing a new method called temporal-differential learning, which includes CT-LSPE and CT-TD, and provides theoretical and empirical evidence of its effectiveness.
In this paper, a new reinforcement learning (RL) method known as the method of temporal differential is introduced. Compared to the traditional temporal-difference learning method, it plays a crucial role in developing novel RL techniques for continuous environments. In particular, the continuous-time least squares policy evaluation (CT-LSPE) and the continuous-time temporal-differential (CT-TD) learning methods are developed. Both theoretical and empirical evidences are provided to demonstrate the effectiveness of the proposed temporal-differential learning methodology.