Approximate solutions to constrained risk-sensitive Markov decision processes.
Uday Kumar MSanjay P. BhatVeeraruna KavithaNandyala HemachandraPublished in: Eur. J. Oper. Res. (2023)
Keyphrases
- risk sensitive
- approximate solutions
- markov decision processes
- np hard
- state space
- dynamic programming
- optimal policy
- reinforcement learning
- finite state
- exact solution
- policy iteration
- optimal solution
- decision processes
- optimal control
- average reward
- infinite horizon
- reinforcement learning algorithms
- average cost
- partially observable
- planning under uncertainty
- action space
- energy function
- sufficient conditions
- partially observable markov decision processes
- lower bound
- heuristic search
- control policies
- markov decision problems
- utility function