Risk-Sensitive Piecewise-Linear Policy Iteration for Stochastic Shortest Path Markov Decision Processes.
Henrique Dias PastorIgor Oliveira BorgesValdinei FreireKarina Valdivia DelgadoLeliane Nunes de BarrosPublished in: MICAI (1) (2020)
Keyphrases
- risk sensitive
- markov decision processes
- stochastic shortest path
- policy iteration
- dynamic programming
- markov decision problems
- optimal policy
- state space
- finite state
- average reward
- average cost
- reinforcement learning
- markov decision process
- planning under uncertainty
- reinforcement learning algorithms
- infinite horizon
- optimal control
- finite horizon
- action space
- decision processes
- partially observable
- linear program
- linear programming
- reward function