Sleeping experts and bandits approach to constrained Markov decision processes.
Hyeong Soo ChangPublished in: Autom. (2016)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- reachability analysis
- policy iteration
- finite horizon
- reinforcement learning algorithms
- model based reinforcement learning
- factored mdps
- markov decision process
- decision theoretic planning
- partially observable
- transition matrices
- planning under uncertainty
- average cost
- risk sensitive
- decision processes
- average reward
- action sets
- semi markov decision processes
- action space
- infinite horizon
- policy evaluation
- monte carlo