Reinforcement learning accelerated by using state transition model with robotic applications.
Kei SendaShinji FujiiSyusuke ManoPublished in: IROS (2004)
Keyphrases
- state transition model
- transition model
- reinforcement learning
- state transition
- state space
- function approximation
- appearance model
- reinforcement learning algorithms
- markov decision problems
- markov decision processes
- multi agent
- optimal policy
- machine learning
- model free
- black box
- relational databases
- state variables
- markov decision process
- hidden markov models
- search algorithm