Coordination in Collaborative Work by Deep Reinforcement Learning with Various State Descriptions.
Yuki MiyashitaToshiharu SugawaraPublished in: PRIMA (2019)
Keyphrases
- reinforcement learning
- multi agent
- multi agent reinforcement learning
- state space
- high level
- learning algorithm
- learning process
- markov decision processes
- distributed agents
- state abstraction
- function approximation
- supervised learning
- partially observable
- state variables
- collaborative learning
- database
- information systems
- neural network