Identification of Blackwell Optimal Policies for Deterministic MDPs.
Victor BooneBruno GaujalPublished in: AISTATS (2023)
Keyphrases
- optimal policy
- markov decision processes
- finite horizon
- state space
- reinforcement learning
- average reward
- decision problems
- dynamic programming
- markov decision process
- average cost
- infinite horizon
- semi markov decision processes
- long run
- policy iteration
- finite state
- multistage
- stationary policies
- state dependent
- serial inventory systems
- initial state
- partially observable
- control policies
- markov decision problems
- bayesian reinforcement learning
- optimal control
- decision diagrams
- dynamic programming algorithms
- discounted reward
- average reward reinforcement learning
- machine learning
- optimal solution
- multi agent
- reinforcement learning algorithms
- sample path
- total cost