On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures.
Guanze PengVeeraruna KavithaQuanyan ZhuPublished in: CoRR (2020)
Keyphrases
- infinite horizon
- optimal control
- average cost
- markov decision processes
- fixed cost
- finite horizon
- dynamic programming
- action space
- reinforcement learning
- optimal policy
- production planning
- control strategy
- policy iteration
- lost sales
- stochastic demand
- finite state
- partially observable
- state space
- markov decision process
- single item
- initial state
- markov decision problems
- stationary policies
- actor critic
- dec pomdps
- average reward
- total cost
- control system
- setup cost
- production cost
- reinforcement learning algorithms