Direct gradient-based reinforcement learning.
Jonathan BaxterPeter L. BartlettPublished in: ISCAS (2000)
Keyphrases
- reinforcement learning
- model free
- function approximation
- optimal policy
- robotic control
- reinforcement learning algorithms
- multi agent
- markov decision processes
- data sets
- state space
- learning algorithm
- supervised learning
- dynamic programming
- evolutionary algorithm
- image sequences
- action selection
- temporal difference
- function approximators
- temporal difference learning
- autonomous learning
- relational reinforcement learning
- genetic algorithm