Q-Learning with Adaptive State Space Construction.
Hajime MuraoShinzo KitamuraPublished in: EWLR (1997)
Keyphrases
- state space
- reinforcement learning
- optimal policy
- reinforcement learning algorithms
- dynamic programming
- heuristic search
- state variables
- dynamical systems
- markov chain
- markov decision processes
- continuous state spaces
- cooperative
- search space
- markov decision process
- particle filter
- action space
- learning agent
- construction process
- partially observable
- reward function
- sufficient conditions
- state transition
- belief state
- learning algorithm
- multi agent
- function approximation
- domain independent
- policy iteration
- mobile robot
- neural network