Multiagent Soft Q-Learning.
Ermo WeiDrew WickeDavid FreelanSean LukePublished in: AAAI Spring Symposia (2018)
Keyphrases
- multi agent
- cooperative
- multiagent learning
- reinforcement learning
- multiagent systems
- multi agent systems
- intelligent agents
- single agent
- multi agent reinforcement learning
- multiple agents
- machine learning
- sufficient conditions
- state space
- autonomous agents
- path planning
- action selection
- decision making
- hard constraints
- learning agents
- stochastic approximation
- data sets