Cooperative Online Learning in Stochastic and Adversarial MDPs.
Tal LancewickiAviv RosenbergYishay MansourPublished in: CoRR (2022)
Keyphrases
- online learning
- cooperative
- markov decision processes
- multi agent
- reinforcement learning
- higher education
- state space
- online course
- distance education
- e learning
- stochastic domains
- monte carlo
- multi agent systems
- blended learning
- finite horizon
- dec pomdps
- computer mediated
- continuous state spaces
- factored mdps
- dynamic programming
- game theory
- control policies
- active learning
- online algorithms
- stochastic programming
- decision theoretic planning
- machine learning