Instance-Based Policy Search using Binomial Distribution Crossover and Iterated Refreshment.
Chikao TsuchiyaKokolo IkedaJun SakumaIsao OnoShigenobu KobayashiPublished in: IEEE Congress on Evolutionary Computation (2006)
Keyphrases
- policy search
- reinforcement learning
- genetic algorithm
- evolutionary algorithm
- genetic programming
- continuous state
- knn
- reinforcement learning algorithms
- dynamic programming
- continuous action
- differential evolution
- policy gradient
- finite state
- reward function
- partially observable markov decision processes
- markov decision processes
- learning algorithm
- machine learning