Batch reinforcement learning in a complex domain.
Shivaram KalyanakrishnanPeter StonePublished in: AAMAS (2007)
Keyphrases
- complex domains
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- batch mode
- machine learning
- markov decision processes
- model free
- multi agent
- temporal difference
- function approximators
- neural network
- bayesian networks
- artificial intelligence
- learning algorithm
- domain knowledge
- dynamic programming
- learning process
- supervised learning
- transfer learning
- domain theory