5 papers
Online Markov Decision Processes with Terminal Law Constraints
Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard +1
Traditional reinforcement learning usually assumes either episodic interactions with resets or continuous operation to minimize average or cumulative loss. While episodic settings…
Online Episodic Convex Reinforcement Learning
Bianca Marin Moreno, Khaled Eldowa, Pierre Gaillard +2
We study online learning in episodic finite-horizon Markov decision processes (MDPs) with convex objective functions, known as the concave utility reinforcement learning (CURL) pro…
MetaCURL: Non-stationary Concave Utility Reinforcement Learning
Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard +1
We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave…
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent
Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard +1
Many machine learning tasks can be solved by minimizing a convex function of an occupancy measure over the policies that generate them. These include reinforcement learning, imitat…
Reimagining Demand-Side Management with Mean Field Learning
Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard +1
Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature. Demand side management (DSM) offers solutions…