Quantized Stationary Control Policies in Markov Decision Processes.
Naci SaldiTamás LinderSerdar YükselPublished in: CoRR (2013)
Keyphrases
- control policies
- markov decision processes
- optimal policy
- action space
- finite horizon
- reinforcement learning
- stationary policies
- state space
- finite state
- non stationary
- continuous state
- dynamic programming
- reward function
- decision problems
- transition matrices
- policy iteration
- infinite horizon
- average reward
- decision theoretic planning
- average cost
- markov decision process
- long run
- sufficient conditions
- partially observable
- initial state
- control policy
- markov chain
- control strategies
- multistage
- control system
- decision making