Adaptive state space partitioning for reinforcement learning.
Ivan S. K. LeeHenry Y. K. LauPublished in: Eng. Appl. Artif. Intell. (2004)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- function approximation
- optimal policy
- heuristic search
- action space
- state abstraction
- adaptive control
- dynamic programming
- partially observable
- state variables
- multi agent
- learning capabilities
- dynamical systems
- continuous state spaces
- temporal difference learning
- goal state
- learning agent
- markov decision process
- learning algorithm
- model free
- particle filter
- markov chain
- search space
- control problems
- initial state
- reward function
- temporal difference
- machine learning
- state and action spaces