Model-based reinforcement learning with nearly tight exploration complexity bounds.
Istvan SzitaCsaba SzepesváriPublished in: ICML (2010)
Keyphrases
- model based reinforcement learning
- complexity bounds
- worst case
- markov decision processes
- upper bound
- lower bound
- reinforcement learning
- constraint networks
- np hard
- query containment
- video sequences
- markov decision problems
- relational domains
- dynamic programming
- state space
- database
- search algorithm
- machine learning