Construction of PSE System for Developing Reinforcement Learning Algorithms.
Taiyo MaedaYusuke AokiTadahiko MurataPublished in: J. Convergence Inf. Technol. (2010)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- eligibility traces
- reinforcement learning problems
- reinforcement learning methods
- function approximation
- learning algorithm
- temporal difference
- reward function
- partially observable environments
- dynamic environments
- stochastic games
- decision making
- machine learning
- monte carlo
- machine learning algorithms
- wavelet transform
- function approximators
- support vector
- policy search