Optimistic Exploration Based on Categorical-DQN for Cooperative Markov Games.
Yu TianChengwei ZhangQing GuoKangjie ZhengWanqing FangXintian ZhaoShiqi ZhangPublished in: DAI (2022)
Keyphrases
- multiagent reinforcement learning
- markov games
- cooperative
- multi agent
- markov decision processes
- multiagent systems
- multi agent systems
- stochastic games
- reinforcement learning algorithms
- markov decision process
- game theory
- reinforcement learning
- hidden markov models
- radial basis function
- nash equilibrium
- multi robot