Reduction of state space on reinforcement learning by sensor selection.
Yasutaka KishimaKentarou KurashigePublished in: MHS (2012)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- heuristic search
- function approximation
- action space
- sensor networks
- markov chain
- markov decision process
- dynamic programming
- machine learning
- learning process
- continuous state spaces
- planning problems
- state variables
- particle filter
- optimal control
- multi agent
- model free
- state abstraction
- sensor data
- selection algorithm
- belief state
- dynamical systems
- partially observable
- control problems
- reduction method
- goal state
- markov decision problems
- state and action spaces
- initial state
- real robot
- action selection
- learning problems
- search space
- multi agent systems
- learning algorithm