Collaborative Multi-agent Stochastic Linear Bandits.
Ahmadreza MoradipariMohammad GhavamzadehMahnoosh AlizadehPublished in: CoRR (2022)
Keyphrases
- multi agent
- stochastic systems
- reinforcement learning
- multiagent environments
- regret bounds
- multiple agents
- intelligent agents
- collaborative learning
- cooperative
- multi user
- multi agent systems
- closed form
- linear model
- team formation
- dynamic programming
- linear systems
- single agent
- agent oriented
- stochastic optimization
- data sets