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