AI Chat AI Image Generator AI Video Text to Speech

Deep Reinforcement Learning in Parameterized Action Space

11/13/2015

∙

by Matthew Hausknecht, et al.

∙

∙

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.

Matthew Hausknecht
23 publications
Peter Stone
126 publications

research

∙ 03/12/2019

Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces

Deep Reinforcement Learning (DRL) has been applied to address a variety ...

0 Haotian Fu, et al. ∙

research

∙ 06/08/2020

Randomized Policy Learning for Continuous State and Action MDPs

Deep reinforcement learning methods have achieved state-of-the-art resul...

11 Hiteshi Sharma, et al. ∙

research

∙ 06/13/2023

Dynamic Interval Restrictions on Action Spaces in Deep Reinforcement Learning for Obstacle Avoidance

Deep reinforcement learning algorithms typically act on the same set of ...

0 Tim Grams, et al. ∙

research

∙ 05/24/2018

A0C: Alpha Zero in Continuous Action Space

A core novelty of Alpha Zero is the interleaving of tree search and deep...

0 Thomas M. Moerland, et al. ∙

research

∙ 05/12/2020

Unbiased Deep Reinforcement Learning: A General Training Framework for Existing and Future Algorithms

In recent years deep neural networks have been successfully applied to t...

0 Huihui Zhang, et al. ∙

research

∙ 05/29/2023

Action valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning

Analysis of invasive sports such as soccer is challenging because the ga...

0 Hiroshi Nakahara, et al. ∙

research

∙ 11/20/2019

Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces

We focus on a class of real-world domains, where gathering hierarchical ...

0 Jaromír Janisch, et al. ∙