Conditions on Preference Relations that Guarantee the Existence of Optimal Policies.
Jonathan Colaco CarrPrakash PanangadenDoina PrecupPublished in: CoRR (2023)
Keyphrases
- optimal policy
- preference relations
- decision problems
- sufficient conditions
- markov decision processes
- stationary policies
- finite horizon
- finite state
- dynamic programming
- multistage
- reinforcement learning
- state space
- pairwise comparisons
- long run
- infinite horizon
- state dependent
- partial order
- desirable properties
- serial inventory systems
- partially observable markov decision processes
- initial state
- markov decision process
- dynamic programming algorithms
- policy iteration
- average cost
- average reward
- lot sizing
- multiple agents
- inventory level
- lost sales
- markov decision problems
- decision theory
- average reward reinforcement learning
- multi attribute