Inducing Cooperation through Reward Reshaping based on Peer Evaluations in Deep Multi-Agent Reinforcement Learning.
David Earl HostalleroDaewoo KimSangwoo MoonKyunghwan SonWan Ju KangYung YiPublished in: AAMAS (2020)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- multi agent
- multi agent systems
- cooperative
- learning agent
- evolutionary game theory
- learning agents
- multi agent learning
- state space
- stochastic games
- machine learning
- function approximation
- game theory
- bayesian networks
- learning algorithm
- markov decision processes
- transfer learning
- information exchange
- long run
- action selection
- reward function
- single agent
- multiagent systems
- sufficient conditions
- learning process
- neural network