Approximation of Convex Envelope Using Reinforcement Learning.
Vivek S. BorkarAdit AkarshPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- convex sets
- function approximation
- convex functions
- state space
- piecewise constant
- learning process
- machine learning
- continuous functions
- convex optimization
- convex hull
- closed form
- approximation algorithms
- multi agent
- error bounds
- markov decision processes
- dynamic programming
- reinforcement learning algorithms
- learning algorithm
- approximation methods
- piecewise linear
- learning problems
- learning tasks
- monte carlo
- image restoration