Variance-Penalized Markov Decision Processes.
Jerzy A. FilarLodewijk C. M. KallenbergHuey-Miin LeePublished in: Math. Oper. Res. (1989)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- policy iteration
- dynamic programming
- least squares
- decision processes
- reinforcement learning
- partially observable
- finite horizon
- transition matrices
- decision theoretic planning
- risk sensitive
- planning under uncertainty
- average cost
- average reward
- model based reinforcement learning
- action space
- reinforcement learning algorithms
- factored mdps
- markov decision process
- loss function
- variance reduction
- reachability analysis
- convergence rate
- decision problems