When is exponential asymptotic optimality achievable in average-reward restless bandits?
Yige HongQiaomin XieYudong ChenWeina WangPublished in: CoRR (2024)
Keyphrases
- genetic algorithm
- asymptotic optimality
- average reward
- asymptotically optimal
- optimal policy
- markov decision processes
- long run
- semi markov decision processes
- sufficient conditions
- sample path
- optimal control
- reinforcement learning
- policy iteration
- stochastic systems
- discounted reward
- model free
- optimality criterion
- decision problems
- markov chain
- dynamic programming
- flowshop
- state and action spaces
- hierarchical reinforcement learning
- simulated annealing
- state space
- finite state
- initial state
- markov decision problems
- average cost
- infinite horizon