A general class of surrogate functions for stable and efficient reinforcement learning.
Sharan VaswaniOlivier BachemSimone TotaroRobert MüllerShivam GargMatthieu GeistMarlos C. MachadoPablo Samuel CastroNicolas Le RouxPublished in: AISTATS (2022)
Keyphrases
- reinforcement learning
- parametric family
- special case
- data mining
- convex functions
- multi class classification
- function approximation
- closely related
- machine learning
- lower bound
- state space
- multi agent systems
- cost effective
- evaluation function
- information systems
- learning algorithm
- aggregation functions
- discrete valued
- neural network