Amanote Research
Register
Sign In
Reinforcement Learning in Multi-Dimensional State-Action Space Using Random Rectangular Coarse Coding and Gibbs Sampling
doi 10.1109/iros.2007.4399401
Full Text
Open PDF
Abstract
Available in
full text
Date
October 1, 2007
Authors
Hajime Kimura
Publisher
IEEE
Related search
Natural Gradient Actor-Critic Algorithms Using Random Rectangular Coarse Coding
State-Action Space Construction for Multi-Layered Learning System.
Journal of the Robotics Society of Japan
Context Transfer in Reinforcement Learning Using Action-Value Functions
Computational Intelligence and Neuroscience
Medicine
Mathematics
Computer Science
Neuroscience
Exploiting Domain Symmetries in Reinforcement Learning With Continuous State and Action Spaces
A Study on Efficient Transfer Learning for Reinforcement Learning Using Sparse Coding
Journal of Automation and Control Engineering
Action-Based State Space Construction for Robot Learning.
Journal of the Robotics Society of Japan
A Comparison of Action Selection Methods for Implicit Policy Method Reinforcement Learning in Continuous Action-Space
Model-Based Reinforcement Learning for Partially Observable Games With Sampling-Based State Estimation
Neural Computation
Arts
Cognitive Neuroscience
Humanities
Multi-Agent Reinforcement Learning in Games
