Deep Reinforcement Learning in Parameterized Action Space

2015-11-13 · Matthew Hausknecht, Peter Stone

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.

📄 PDF Abstract BibTeX arXiv:1511.04143

Code (7)

mhauskn/dqn-hfo 공식 구현

MLCS-Yonsei/ddpg-control tf

cycraig/MP-DQN pytorch

ltzheng/pddpg-hfo pytorch

opendilab/DI-engine pytorch

stevenpjg/ddpg-aigym tf

thainv0212/re-ddpg tf

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space

2019-03-04 · Zhou Fan, Rui Su, Wei-Nan Zhang, Yong Yu

In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured actio…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space

2018-10-23 · Ermo Wei, Drew Wicke, Sean Luke

We explore Deep Reinforcement Learning in a parameterized action space. Specifically, we investigate how to achieve sample-efficient end-to-end training in these tasks. We propose a new compact architecture for the tasks…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions

2025-12-23 · Rashmeet Kaur Nayyar, Naman Shah, Siddharth Srivastava arxiv

Real-world sequential decision-making often involves parameterized action spaces that require both, decisions regarding discrete actions and decisions about continuous action parameters governing how an action is execute…

Reinforcement Learning

Model-based Reinforcement Learning for Parameterized Action Spaces

2024-04-03 · Renhao Zhang, Haotian Fu, Yilin Miao, George Konidaris

We propose a novel model-based reinforcement learning algorithm -- Dynamics Learning and predictive control with Parameterized Actions (DLPA) -- for Parameterized Action Markov Decision Processes (PAMDPs). The agent lear…

model Model-based Reinforcement Learning reinforcement-learning Reinforcement Learning

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

2019-03-12 · Haotian Fu, Hongyao Tang, Jianye Hao, Zihan Lei 외

Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previo…

Deep Reinforcement Learning Multi-agent Reinforcement Learning Q-Learning reinforcement-learning+2