A Topology for Policies in Decentralized Stochastic Control and Existence of Optimal Policies.
Naci SaldiPublished in: CDC (2018)
Keyphrases
- optimal policy
- stochastic control
- optimal control
- dynamic programming
- reinforcement learning
- control problems
- markov decision processes
- decision problems
- queueing systems
- operations management
- finite horizon
- state space
- brownian motion
- multistage
- serial inventory systems
- finite state
- long run
- stationary policies
- infinite horizon
- markov decision process
- control policies
- average reward
- multi agent
- average cost
- inventory level
- state dependent
- partially observable markov decision processes
- initial state
- reward function
- lost sales
- sufficient conditions
- markov decision problems
- learning algorithm
- cost function