Exploration for Multi-task Reinforcement Learning with Deep Generative Models. (arXiv:1611.09894v1 [cs.AI])

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We evaluate our method on a new set of environments and provide intuitive interpretation of our results.

from cs.AI updates on arXiv.org http://ift.tt/2gzSmdc
via IFTTT