Solving Multi-objective Reinforcement Learning Problems by EDA-RL - Acquisition of Various Strategies.
Hisashi HandaPublished in: ISDA (2009)
Keyphrases
- reinforcement learning problems
- multi objective
- reinforcement learning algorithms
- markov decision problems
- reinforcement learning
- reinforcement learning methods
- temporal difference methods
- evolutionary algorithm
- optimization algorithm
- multi objective optimization
- policy iteration
- function approximation
- model free
- markov decision processes
- state space
- particle swarm optimization
- objective function
- optimal policy
- partially observable
- differential evolution
- linear programming
- temporal difference
- function approximators
- multiple objectives
- decision theoretic
- neural network
- multi agent
- learning algorithm
- genetic algorithm
- evolutionary computation
- stochastic games
- machine learning
- action selection
- control strategies
- least squares
- optimal strategy
- nsga ii
- utility function