Reinforcement Learning via AIXI Approximation
Joel VenessKee Siong NgMarcus HutterDavid SilverPublished in: CoRR (2010)
Keyphrases
- reinforcement learning
- function approximation
- sequence prediction
- state space
- closed form
- reinforcement learning algorithms
- robotic control
- approximation methods
- approximation error
- relative error
- multi agent
- markov decision processes
- approximation algorithms
- learning classifier systems
- temporal difference learning
- markov decision process
- data sets
- transition model
- reinforcement learning methods
- optimal solution
- probability distribution
- learning agent
- error bounds
- queueing networks
- temporal difference
- markov models
- optimal control