Quad-Q-learning.
Clifford ClausenHarry WechslerPublished in: IEEE Trans. Neural Networks Learn. Syst. (2000)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- cooperative
- reinforcement learning algorithms
- multi agent
- state space
- optimal policy
- learning rate
- action selection
- stochastic approximation
- model free
- bucket brigade
- potential field
- stochastic shortest path
- multi agent reinforcement learning
- temporal difference
- single agent
- policy iteration
- markov decision processes
- learning process
- information retrieval
- data mining
- credit assignment
- neural network