Reinforcement Learning in Large State Spaces.
Karl TuylsSam MaesBernard ManderickPublished in: RoboCup (2002)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- optimal policy
- heuristic search
- dynamic programming
- function approximation
- action space
- markov chain
- state abstraction
- model free
- planning problems
- particle filter
- orders of magnitude
- dynamical systems
- partially observable
- control problems
- continuous state spaces
- heuristic function
- transfer learning
- reinforcement learning methods
- continuous state
- learning algorithm
- machine learning
- data mining
- policy search
- markov decision process
- belief state
- temporal difference
- initial state
- reward function
- markov decision problems
- optimal control
- search algorithm
- data sets
- robotic control
- fitted q iteration