Multiagent Cooperation and Competition with Deep Reinforcement Learning.
Ardi TampuuTambet MatiisenDorian KodeljaIlya KuzovkinKristjan KorjusJuhan AruJaan AruRaul VicentePublished in: CoRR (2015)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- multi agent systems
- multi agent environments
- function approximation
- intelligent agents
- single agent
- reinforcement learning algorithms
- multi agent reinforcement learning
- model free
- autonomous agents
- learning agents
- temporal difference
- multiple agents
- multiagent systems
- learning algorithm
- multiagent learning
- learning problems
- software agents
- optimal policy
- machine learning
- temporal difference learning
- distributed problem solving
- international competition
- markov decision process
- action selection
- evaluation function
- information sharing
- transfer learning
- supervised learning