Real-world reinforcement learning (RL) applications often come with possibly infinite state and action space, and in such a situation classical RL algorithms developed in the tabular setting are not applicable anymore. A popular approach to overcoming this issue is by applying function approximation techniques to the underlying structures of the Markovdecision processes (MDPs).

InProceedingsofthe First International Conferenceon Distributed Artificial Intelligence, pages 1-7, 2019.

Importantly, E2 is bounded independently ofS.

Weevaluate PI-SAC agents by comparing against uncompressed PI-SAC agents, other compressed and uncompressed agents, and SAC agents directly trained from pixels.

A deep visual tracker is typically based on either object detection or template matching while each of them is only suitable for a particular group of scenes. It is straightforward to consider fusing them together to pursue more reliable tracking. However, this is not wise as they follow different tracking principles.

DDPG [24]extends Q-learning to continuous control based on the Deterministic Policy Gradient [31] algorithm, which learns a deterministic policyπ(s;φ) parameterized byφto maximize the Q-function to approximate themaxoperator.