On Online Learning in Kernelized Markov Decision Processes
This work addresses the challenge of online learning in complex, continuous environments for reinforcement learning applications, representing an incremental improvement with a novel method for a known bottleneck.
The authors tackled the problem of learning episodic Markov decision processes with continuous state and action spaces by developing algorithms based on kernel approximation techniques, achieving low regret results.
We develop algorithms with low regret for learning episodic Markov decision processes based on kernel approximation techniques. The algorithms are based on both the Upper Confidence Bound (UCB) as well as Posterior or Thompson Sampling (PSRL) philosophies, and work in the general setting of continuous state and action spaces when the true unknown transition dynamics are assumed to have smoothness induced by an appropriate Reproducing Kernel Hilbert Space (RKHS).