Consensus achievement strategy of opinion dynamics based on deep reinforcement learning with time constraint.
Mingwei WangDecui LiangZeshui XuPublished in: J. Oper. Res. Soc. (2022)
Keyphrases
- reinforcement learning
- function approximation
- learning process
- constraint solving
- multi agent
- optimal policy
- robotic control
- linear constraints
- reinforcement learning algorithms
- optimal strategy
- learning classifier systems
- search strategy
- learning algorithm
- state space
- case study
- decision making
- information systems