Risk-Sensitive Average Optimality for Discrete-Time Markov Decision Processes.
Xian ChenQingda WeiPublished in: SIAM J. Control. Optim. (2023)
Keyphrases
- risk sensitive
- markov decision processes
- average cost
- finite state
- stationary policies
- semi markov decision processes
- optimal policy
- average reward
- reinforcement learning
- state space
- finite horizon
- dynamic programming
- policy iteration
- planning under uncertainty
- markov decision process
- infinite horizon
- long run
- initial state
- decision processes
- markov chain
- reinforcement learning algorithms
- optimal control
- action space
- multi agent
- partially observable markov decision processes
- decision problems
- control policy
- linear programming
- markov decision problems
- sufficient conditions
- learning algorithm
- np hard
- multistage
- reward function
- machine learning