Collaborative Learning and Personalization in Multi-Agent Stochastic Linear Bandits.
Avishek GhoshAbishek SankararamanKannan RamchandranPublished in: CoRR (2021)
Keyphrases
- collaborative learning
- multi agent
- regret bounds
- stochastic systems
- computer mediated
- learning outcomes
- cooperative
- monte carlo
- individual learning
- online learning
- reinforcement learning
- multiple knowledge sources
- multi armed bandits
- group formation
- simple linear
- linear systems
- learning process
- multi agent systems
- learning algorithm
- stochastic model
- knowledge construction
- user modeling
- content analysis
- multiagent systems
- collaborative learning activities
- heterogeneous agents
- chance constraints
- optimal solution