Rationality of Reward Sharing in Multi-agent Reinforcement Learning.
Kazuteru MiyazakiShigenobu KobayashiPublished in: New Gener. Comput. (2001)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- multi agent
- learning agent
- multi agent learning
- learning agents
- game theory
- multi agent systems
- state space
- knowledge sharing
- reinforcement learning algorithms
- average reward
- stochastic games
- information sharing
- markov decision processes
- machine learning
- function approximation
- reward function
- learning algorithm