On the Effects of Domain Size and Complexity in Empirical Distribution of Reinforcement Learning.
Kazunori IwataKazushi IkedaHideaki SakaiPublished in: IEICE Trans. Inf. Syst. (2005)
Keyphrases
- reinforcement learning
- space complexity
- computational complexity
- domain specific
- machine learning
- space requirements
- domain independent
- worst case time complexity
- optimal policy
- maximum number
- real time
- network size
- learning process
- domain experts
- multi agent
- markov decision processes
- function approximation
- information systems
- model free
- robotic control