Fixed-point equations solving Risk-sensitive MDP with constraint.
Vartika SinghVeeraruna KavithaPublished in: ACC (2023)
Keyphrases
- fixed point
- risk sensitive
- markov decision problems
- policy iteration
- markov decision processes
- utility function
- linear programming
- dynamical systems
- partially observable
- state space
- optimal policy
- optimal control
- reinforcement learning
- sufficient conditions
- mathematical model
- average cost
- decision processes
- belief propagation
- differential equations
- dynamic programming
- decision theoretic
- model free
- expected utility
- queueing networks
- variational inequalities
- infinite horizon
- markov decision process
- finite state
- action space
- decision makers
- linear program
- finite horizon
- function approximators
- average reward
- markov random field