Convex Reinforcement Learning in Finite Trials.
Mirco MuttiRiccardo De SantiPiersilvio De BartolomeisMarcello RestelliPublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- reinforcement learning
- state and action spaces
- function approximation
- convex optimization
- state space
- markov decision processes
- reinforcement learning algorithms
- machine learning
- model free
- temporal difference
- learning algorithm
- action space
- finite dimensional
- dynamic programming
- convex hull
- semidefinite
- temporal difference learning
- markov decision problems
- multi agent
- robotic control
- piecewise linear
- partially observable
- convex programming
- transition model