Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor.
Julien Grand-ClémentMarek PetrikPublished in: CoRR (2023)
Keyphrases
- machine learning
- discount factor
- average cost
- markov decision processes
- average reward
- optimal policy
- reinforcement learning
- discounted reward
- infinite horizon
- markov decision problems
- long run
- finite horizon
- finite state
- stationary policies
- state space
- decision problems
- learning algorithm
- policy iteration
- reinforcement learning algorithms
- optimal control
- finite number
- partially observable
- multistage
- total cost
- model free
- linear programming
- dynamic programming
- sample path
- markov chain
- decision processes
- domain independent
- linear program
- sufficient conditions
- markov decision process
- initial state
- function approximation
- situation calculus