State transition rate based reinforcement learning.
Takeshi OhashiHirohiko NakamuraJunichi MinatodaniShuichi EnokidaTakaichi YoshidaToshiaki EjimaPublished in: SMC (2000)
Keyphrases
- state transition
- reinforcement learning
- state space
- transition model
- input output
- state transition model
- state transitions
- black box
- hidden markov models
- finite state machines
- markov chain
- reinforcement learning algorithms
- function approximation
- markov decision processes
- optimal policy
- temporal difference
- probability distribution
- model free
- dynamic programming
- multi agent
- decision problems
- optimal control
- action space
- video sequences
- machine learning
- particle filter
- linear programming
- internal state
- learning algorithm