Deep Reinforcement Learning In Parameterized Action Space

# Deep Reinforcement Learning in Parameterized Action Space

**arXiv ID:** 1511.04143
**Authors:** Matthew Hausknecht, Peter Stone
**Published:** 2015-11-13T02:34:33Z
**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.

## Skill Description

This skill is generated from the arXiv paper: Deep Reinforcement Learning in Parameterized Action Space (1511.04143).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1511.04143](http://arxiv.org/abs/1511.04143v5)