High-Dimensional Function Approximation for Knowledge-Free Reinforcement Learning: a Case Study in SZ-Tetris.
Wojciech JaskowskiMarcin Grzegorz SzubertPawel LiskowskiKrzysztof KrawiecPublished in: GECCO (2015)
Keyphrases
- function approximation
- reinforcement learning
- high dimensional
- function approximators
- temporal difference
- tile coding
- mountain car
- temporal difference learning
- model free
- temporal difference learning algorithms
- state action space
- state space
- reinforcement learning algorithms
- dimensionality reduction
- radial basis function
- machine learning
- markov decision processes
- learning tasks
- pattern recognition
- neural network
- transfer learning
- learning algorithm
- multi agent
- actor critic
- feature space
- active learning
- nearest neighbor
- learning process
- control policy
- dynamic programming
- evaluation function
- genetic algorithm
- optimal policy