DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs.
Khaled NakhlehI-Hong HouPublished in: NeurIPS (2022)
Keyphrases
- optimal policy
- markov decision processes
- finite horizon
- state space
- reinforcement learning
- decision problems
- average reward
- policy iteration
- infinite horizon
- markov decision process
- dynamic programming
- finite state
- long run
- long run average cost
- average cost
- state dependent
- markov decision problems
- multistage
- reward function
- discount factor
- control policies
- initial state
- partially observable
- dynamic programming algorithms
- bayesian reinforcement learning
- sufficient conditions
- lost sales
- inventory level
- machine learning
- serial inventory systems