6 papers
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
Claire Vernade, Onno Eberhard, Martha White +4
Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields…
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
Yike Zhao, Onno Eberhard, Malek Khammassi +2
The family of linear recurrent neural networks has shown strong performance as recurrent memory units in partially observable reinforcement learning. We provide a theoretical justi…
Commit to the Bit: Reactive Reinforcement Learning Done Right
Onno Eberhard, Claire Vernade, Michael Muehlebach
Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either par…
Middle-mile logistics through the lens of goal-conditioned reinforcement learning
Onno Eberhard, Thibaut Cuvelier, Michal Valko +1
Middle-mile logistics describes the problem of routing parcels through a network of hubs linked by trucks with finite capacity. We rephrase this as a multi-object goal-conditioned…
Partially Observable Reinforcement Learning with Memory Traces
Onno Eberhard, Michael Muehlebach, Claire Vernade
Partially observable environments present a considerable computational challenge in reinforcement learning due to the need to consider long histories. Learning with a finite window…
A Pontryagin Perspective on Reinforcement Learning
Onno Eberhard, Claire Vernade, Michael Muehlebach
Reinforcement learning has traditionally focused on learning state-dependent policies to solve optimal control problems in a closed-loop fashion. In this work, we introduce the par…