Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes
This work addresses value function approximation for reinforcement learning in large or continuous state spaces, offering incremental improvements in robustness and adaptability.
The paper tackles policy evaluation in reinforcement learning by developing online scalable Gaussian process temporal-difference (OS-GPTD) and ensemble (OS-EGPTD) methods to estimate value functions, achieving competitive performance on benchmark problems with worst-case error bounds.
Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous. The present paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning, where a Gaussian process (GP) prior is presumed on the sought value function, and instantaneous rewards are probabilistically generated based on value function evaluations at two consecutive states. Capitalizing on a random feature-based approximant of the GP prior, an online scalable (OS) approach, termed {OS-GPTD}, is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To benchmark the performance of OS-GPTD even in an adversarial setting, where the modeling assumptions are violated, complementary worst-case analyses are performed by upper-bounding the cumulative Bellman error as well as the long-term reward prediction error, relative to their counterparts from a fixed value function estimator with the entire state-reward trajectory in hindsight. Moreover, to alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme, termed OS-EGPTD, that can jointly infer the value function, and select interactively the EGP kernel on-the-fly. Finally, performances of the novel OS-(E)GPTD schemes are evaluated on two benchmark problems.