The Penalty Avoiding Rational Policy Making Algorithm in Continuous Action Spaces.
Kazuteru MiyazakiPublished in: IDEAL (2010)
Keyphrases
- dynamic programming
- objective function
- computational complexity
- action space
- np hard
- continuous state spaces
- sufficient conditions
- optimal solution
- reinforcement learning
- learning algorithm
- multi agent
- search space
- bayesian networks
- decision making
- mobile robot
- probabilistic model
- state space
- markov random field
- dynamic environments
- decision problems
- databases
- data sets