Deep Reinforcement Learning in Parameterized Action Space
It addresses the challenge of handling complex action spaces in reinforcement learning for domains like simulated RoboCup soccer, representing an incremental extension to existing methods.
This paper tackled the problem of applying deep reinforcement learning to structured parameterized continuous action spaces, achieving a result where the best learned agent scored goals more reliably than the 2012 RoboCup champion agent.
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, each of which is parameterized with continuous variables. The best learned agent can score goals more reliably than the 2012 RoboCup champion agent. As such, this paper represents a successful extension of deep reinforcement learning to the class of parameterized action space MDPs.