• Home
  • Search
  • Relevance Vector Sampling for Reinforcement Learning in Continuous Action Space
  • Cite Icon3
  • https://doi.org/10.1109/icmla.2016.0138Copy DOI Icon

Relevance Vector Sampling for Reinforcement Learning in Continuous Action Space

  • Dec 1, 2016
  • Minwoo Lee +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

To be applicable to real world problems, much reinforcement learning (RL) research has focused on continuous state spaces with function approximations. Some problems also require continuous actions, but searching for good actions in a continuous action space is problematic. This paper suggests a novel relevance vector sampling approach to action search in an RL framework with relevance vector machines (RVM-RL). We hypothesize that each relevance vector (RV) is placed on the modes of the value approximation surface as the learning converges. From the hypothesis, we select actions in RVs to maximize the estimated state-action values. We report the efficiency of the proposed approach by controlling a simulated octopus arm with RV-sampled actions.

Similar Papers
  • Conference Article
  • Citations3

A reinforcement learning algorithm developed to model GenCo strategic bidding behavior in multidimensional and continuous state and action spaces

  • Apr 01, 2013
  • Alfred Yong Fu Lau +2
  • Conference Article
  • Citations232

Reinforcement Learning in Continuous Action Spaces

  • Apr 01, 2007
  • Hado Van Hasselt +1
  • Research Article
  • Citations68

A data-driven output voltage control of solid oxide fuel cell using multi-agent deep reinforcement learning

  • Sep 09, 2021
  • Applied Energy
  • Jiawen Li +2
  • Conference Article
  • Citations151

Networked Multi-Agent Reinforcement Learning in Continuous Spaces

  • Dec 01, 2018
  • Kaiqing Zhang +2
  • Research Article
  • Citations5

Representation learning for continuous action spaces is beneficial for efficient policy learning

  • Dec 16, 2022
  • Neural Networks
  • Tingting Zhao +5
  • Research Article
  • Citations4

Active Inference and Reinforcement Learning: A Unified Inference on Continuous State and Action Spaces Under Partial Observability.

  • Sep 17, 2024
  • Neural computation
  • Parvin Malekzadeh +1
  • Research Article
  • Citations8

A Study of Continuous Maximum Entropy Deep Inverse Reinforcement Learning

  • Jan 01, 2019
  • Mathematical Problems in Engineering
  • Xi-Liang Chen +4
  • Research Article
  • Citations9

Observation-Based Optimization for POMDPs With Continuous State, Observation, and Action Spaces

  • May 01, 2019
  • IEEE Transactions on Automatic Control
  • Xiaofeng Jiang +3
  • Conference Article
  • Citations1

Optimal Rate Control for Latency-constrained High Throughput Big Data Applications

  • Dec 17, 2022
  • Ziren Xiao +2
  • Conference Article
  • Citations9

On-line Energy Optimization of Hybrid Production Systems Using Actor-Critic Reinforcement Learning

  • Sep 01, 2018
  • Dorothea Schwung +2
  • Conference Article
  • Citations36

Beating the Stock Market with a Deep Reinforcement Learning Day Trading System

  • Jul 01, 2020
  • Leonardo Conegundes +1
  • Conference Article
  • Citations363

PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning

  • May 01, 2018
  • Aleksandra Faust +6
  • Research Article
  • Citations2

Efficient Exploration in Large State-Action Space Through Structured Action Space for Learning Multirobots Motion Planning

  • Jan 01, 2025
  • IEEE Transactions on Control Systems Technology
  • Chaoxu Mu +5
  • Research Article
  • Citations13

Modeling-Learning-Based Actor-Critic Algorithm with Gaussian Process Approximator

  • Apr 18, 2020
  • Journal of Grid Computing
  • Shan Zhong +5
  • Research Article

Reinforcement Learning with Autonomous Segmentation for Continuous State and Action Spaces

  • Jan 01, 2002
  • Transactions of the Institute of Systems, Control and Information Engineers
  • Kazuaki Yamada +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.