Universal Reinforcement Learning
Vivek F. FariasCiamac Cyrus MoallemiTsachy WeissmanBenjamin Van RoyPublished in: CoRR (2007)
Keyphrases
- reinforcement learning
- model free
- sequence prediction
- state space
- function approximation
- markov decision processes
- optimal policy
- databases
- reinforcement learning algorithms
- supervised learning
- learning problems
- learning process
- multi agent
- kolmogorov complexity
- learning algorithm
- temporal difference learning
- robot control
- robotic control
- machine learning
- algorithmic information theory
- relational reinforcement learning
- real time
- policy search
- action space
- partially observable
- multi valued
- real world
- information systems
- knowledge base
- website
- dynamic programming