Acquisition of cooperative behaviour among heterogeneous agents using step-up reinforcement learning.
Wataru SatoKanta TachibanaPublished in: APSITT (2015)
Keyphrases
- heterogeneous agents
- multi agent
- cooperative
- reinforcement learning
- autonomous agents
- distributed search
- multi agent systems
- multi agent reinforcement learning
- conflict management
- markov decision processes
- intelligent agents
- dynamic environments
- state space
- optimal policy
- multiagent systems
- fault tolerance
- reward function