Reinforcement Learning for Penalty Avoidance in Continuous State Spaces.
Kazuteru MiyazakiShigenobu KobayashiPublished in: J. Adv. Comput. Intell. Intell. Informatics (2007)
Keyphrases
- continuous state spaces
- reinforcement learning
- state space
- continuous state
- action space
- control problems
- markov decision processes
- function approximation
- optimal policy
- rl algorithms
- dynamic programming
- machine learning
- heuristic search
- learning problems
- reinforcement learning algorithms
- markov decision problems
- partially observable markov decision processes
- stochastic processes
- model free
- temporal difference
- robot navigation
- optimal control
- search space
- objective function
- learning algorithm
- adaptive control
- control policies