Qualitative Transfer for Reinforcement Learning with Continuous State and Action Spaces.
Esteban Omar GarciaEnrique Munoz de CoteEduardo F. MoralesPublished in: CIARP (1) (2013)
Keyphrases
- continuous state and action spaces
- reinforcement learning
- transfer learning
- continuous state
- action selection
- function approximators
- function approximation
- state space
- multi agent
- model free
- learning tasks
- temporal difference
- optimal policy
- learning algorithm
- supervised learning
- markov decision processes
- decision theory
- dynamic programming
- neural network
- action space
- average reward
- temporal difference learning
- rl algorithms
- decision making
- sparse approximation
- model checking