Stochastic Comparative Statics in Markov Decision Processes.
Bar LightPublished in: Math. Oper. Res. (2021)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- state space
- policy iteration algorithm
- reinforcement learning
- policy iteration
- dynamic programming
- reinforcement learning algorithms
- decision theoretic planning
- planning under uncertainty
- transition matrices
- decision processes
- factored mdps
- reachability analysis
- reward function
- semi markov decision processes
- markov decision process
- partially observable
- infinite horizon
- finite horizon
- state dependent
- stochastic processes
- average reward
- risk sensitive
- monte carlo
- average cost
- continuous state spaces
- action sets
- linear programming
- least squares
- search algorithm