Deep Reinforcement Learning in Parameterized Action Space

Code

• github.com/mhauskn/dqn-hfo
  OfficialIn papernone★ 0
• github.com/stevenpjg/ddpg-aigym
  tf★ 276
• github.com/MLCS-Yonsei/ddpg-control
  tf★ 1
• github.com/cycraig/MP-DQN
  pytorch★ 0
• github.com/thainv0212/re-ddpg
  tf★ 0
• github.com/ltzheng/pddpg-hfo
  pytorch★ 0

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, 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.

Tasks

Reproductions