Concurrent Q-learning: Reinforcement learning for dynamic goals and environments.
Robert OllingtonPeter VamplewPublished in: Int. J. Intell. Syst. (2005)
Keyphrases
- reinforcement learning
- function approximation
- dynamic environments
- hierarchical reinforcement learning
- model free
- reinforcement learning algorithms
- state space
- multi agent
- action selection
- optimal policy
- cooperative
- learning algorithm
- temporal difference
- highly dynamic
- markov decision processes
- multi agent environments
- multi agent reinforcement learning
- real world
- policy iteration
- stochastic approximation
- reinforcement learning methods
- single agent
- multiagent learning
- temporal difference learning
- dynamic programming
- function approximators
- optimal control
- robotic systems