CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning.
Jiachen YangAlireza NakhaeiDavid IseleKikuo FujimuraHongyuan ZhaPublished in: ICLR (2020)
Keyphrases
- multistage
- multi agent reinforcement learning
- cooperative
- stochastic programming
- multi agent
- dynamic programming
- single stage
- multi agent systems
- lot sizing
- stochastic optimization
- multi agent learning
- reinforcement learning
- optimal policy
- learning agents
- stochastic games
- information processing
- distributed control
- neural network
- linear programming
- search algorithm
- artificial intelligence