Reinforcement Learning via AIXI Approximation.
Joel VenessKee Siong NgMarcus HutterDavid SilverPublished in: AAAI (2010)
Keyphrases
- reinforcement learning
- function approximation
- error bounds
- approximation algorithms
- sequence prediction
- learning algorithm
- optimal control
- markov decision process
- policy evaluation
- data sets
- temporal difference
- multi agent
- search space
- optimal policy
- real time
- machine learning
- learning agent
- reinforcement learning methods
- policy search