EDA-RL: estimation of distribution algorithms for reinforcement learning problems.
Hisashi HandaPublished in: GECCO (2009)
Keyphrases
- estimation of distribution algorithms
- reinforcement learning problems
- reinforcement learning algorithms
- reinforcement learning
- feature subset selection
- reinforcement learning methods
- evolutionary computation
- particle swarm optimization algorithm
- evolutionary algorithm
- temporal difference methods
- policy iteration
- continuous domains
- function approximation
- multi objective optimization
- function approximators
- multi objective
- model free
- genetic programming
- markov decision processes
- state space
- combinatorial optimization
- combinatorial optimization problems
- markov decision problems
- genetic algorithm
- action space
- temporal difference
- learning algorithm
- particle swarm optimization
- dynamical systems
- reward function
- optimal policy
- control problems
- computational intelligence
- kernel function
- machine learning
- markov decision process
- simulated annealing
- dynamic programming
- convergence speed