Reinforcement Learning in Quasi-Continuous Time.
Pawel WawrzynskiAndrzej PacutPublished in: CIMCA/IAWTIC (2005)
Keyphrases
- reinforcement learning
- optimal control
- state space
- dynamical systems
- reinforcement learning algorithms
- function approximation
- machine learning
- markov processes
- dynamic programming
- markov chain
- model free
- markov decision processes
- control problems
- optimal policy
- learning algorithm
- semi markov decision process
- markov decision process
- data sets
- learning process
- temporal difference
- learning problems
- reinforcement learning methods
- multi agent reinforcement learning
- robotic control
- transfer learning
- probability distribution
- evolutionary algorithm
- decision making
- partially observable
- genetic algorithm
- temporal difference learning