Time manipulation technique for speeding up reinforcement learning in simulations
Petar KormushevKohei NomotoFangyan DongKaoru HirotaPublished in: CoRR (2009)
Keyphrases
- reinforcement learning
- state space
- function approximation
- markov decision processes
- model free
- control problems
- learning algorithm
- reinforcement learning algorithms
- numerical simulations
- optimal policy
- machine learning
- temporal difference
- optimal control
- supervised learning
- dynamic programming
- simulation model
- special case
- multi agent
- objective function
- case study
- simulation environment
- information systems
- mathematical analysis
- data mining
- function approximators
- stochastic approximation
- robotic control