Adaptive Play Q-Learning with Initial Heuristic Approximation.
Andriy BurkovBrahim Chaib-draaPublished in: ICRA (2007)
Keyphrases
- cooperative
- reinforcement learning
- dynamic programming
- multi agent
- simulated annealing
- worst case analysis
- learning algorithm
- genetic algorithm
- optimal solution
- evolutionary algorithm
- state space
- machine learning
- closed form
- approximation algorithms
- game playing
- search algorithm
- combinatorial optimization
- error bounds
- action selection
- reinforcement learning algorithms
- approximation methods
- greedy heuristic