Online Markov Decision Processes Under Bandit Feedback.
Gergely NeuAndrás GyörgyCsaba SzepesváriAndrás AntosPublished in: IEEE Trans. Autom. Control. (2014)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- policy iteration
- dynamic programming
- transition matrices
- reinforcement learning
- reinforcement learning algorithms
- reachability analysis
- decision theoretic planning
- markov chain
- infinite horizon
- online learning
- model based reinforcement learning
- planning under uncertainty
- finite horizon
- factored mdps
- partially observable
- reward function
- average reward
- risk sensitive
- decision processes
- state and action spaces
- average cost
- semi markov decision processes
- action sets
- action space
- search space