Examining Average and Discounted Reward Optimality Criteria in Reinforcement Learning.
Vektor DewantoMarcus GallagherPublished in: AI (2022)
Keyphrases
- discounted reward
- optimality criteria
- reinforcement learning
- markov decision processes
- average reward
- state and action spaces
- policy iteration
- optimal policy
- hierarchical reinforcement learning
- state space
- reinforcement learning algorithms
- model free
- action space
- dynamic programming
- average cost
- long run
- temporal difference
- finite state
- markov decision problems
- optimality criterion
- partially observable
- markov decision process
- function approximation
- learning algorithm
- action selection
- decision problems
- supervised learning
- multi agent
- objective function