Online Convex Optimization in Adversarial Markov Decision Processes.
Aviv RosenbergYishay MansourPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- online convex optimization
- long run
- optimal policy
- online learning
- finite state
- convex optimization
- reinforcement learning
- dynamic programming
- policy iteration
- state space
- newton method
- transition matrices
- markov decision process
- decision theoretic planning
- efficient algorithms for solving
- average cost
- reinforcement learning algorithms
- action space
- average reward
- cost function
- multi agent
- least squares
- feature selection
- infinite horizon