Cooperative Online Learning in Stochastic and Adversarial MDPs.
Tal LancewickiAviv RosenbergYishay MansourPublished in: ICML (2022)
Keyphrases
- online learning
- cooperative
- markov decision processes
- multi agent
- distance learning
- factored mdps
- online course
- reinforcement learning
- e learning
- higher education
- state space
- active learning
- distance education
- optimal policy
- continuous state spaces
- blended learning
- monte carlo
- computer mediated
- partially observable
- markov decision problems
- cooperative learning
- decision theoretic planning
- game theory
- multi agent systems
- stochastic domains
- reward function
- finite state
- learning environment
- learning process
- linear programming