Deep Reinforcement Learning in Parameterized Action Space

arXiv:1511.04143v5 Announce Type: replace-cross
Abstract: Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains featuring continuous state and action spaces. However, to the best of our knowledge no previous work has succeeded at using deep neural networks in structured (parameterized) continuous action spaces. To fill this gap, this paper focuses on learning within the domain of simulated RoboCup soccer, which features a small set of discrete action types, …

abstract arxiv best of continuous cs.ai cs.lg cs.ma cs.ne domains functions however knowledge networks neural networks policies reinforcement reinforcement learning space spaces state type value work