Choatic GA Based Q-Learning in Nondeterministic Maze Benchmark.
Mostafa RafieiMajid SinaPublished in: ICCSA (Short Papers/poster papers/PhD student showcase works) (2015)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- state space
- action selection
- cooperative
- genetic algorithm ga
- genetic algorithm
- learning algorithm
- finite automata
- optimal policy
- hierarchical reinforcement learning
- machine learning
- potential field
- learning rate
- simulated annealing
- comparative analysis
- markov chain
- reinforcement learning algorithms
- dynamic programming
- search algorithm