Reinforcement Learning Via Practice and Critique Advice.
Kshitij JudahSaikat RoyAlan FernThomas G. DietterichPublished in: AAAI (2010)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- temporal difference
- database systems
- optimal policy
- dynamic environments
- markov decision processes
- action selection
- multi agent
- clustering algorithm
- artificial intelligence
- database
- databases
- real time
- robotic control
- multi agent reinforcement learning
- transition model
- dynamic programming
- control system
- artificial neural networks
- multiscale
- feature selection
- learning algorithm
- machine learning
- real world