Coordination in Large Multiagent Reinforcement Learning Problems.
Thomas KemmerichHans Kleine BüningPublished in: IAT (2011)
Keyphrases
- reinforcement learning problems
- multi agent
- multiagent systems
- reinforcement learning
- reinforcement learning algorithms
- cooperative
- multi agent systems
- multiple agents
- reinforcement learning methods
- markov decision problems
- action space
- function approximation
- single agent
- policy iteration
- function approximators
- state space
- model free
- reward function
- markov decision processes
- random walk
- least squares
- machine learning
- neural network
- temporal difference
- learning algorithm