Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning.
Harm van SeijenMehdi FatemiArash TavakoliPublished in: NeurIPS (2019)
Keyphrases
- reinforcement learning
- factors that influence
- function approximation
- factors affecting
- state space
- learning algorithm
- model free
- multi agent
- factors that affect
- worst case
- dynamic environments
- policy search
- machine learning
- significantly lower
- factors influencing
- transfer learning
- optimal policy
- learning process
- metadata
- e learning