Reinforcement learning facilitates an optimal interaction intensity for cooperation.
Zhao SongHao GuoDanyang JiaMatjaz PercXuelong LiZhen WangPublished in: Neurocomputing (2022)
Keyphrases
- reinforcement learning
- cooperative
- dynamic programming
- multi agent
- human computer interaction
- optimal control
- control policy
- markov decision processes
- optimal strategy
- optimal design
- approximate dynamic programming
- data sets
- policy iteration
- reinforcement learning algorithms
- model free
- hidden markov models
- learning algorithm
- genetic algorithm
- neural network