Gaspard Lambrechts

Postdoctorat - McGill

Superviseur⋅e principal⋅e

Aditya Mahajan

Co-supervisor

Pierre-Luc Bacon

Sujets de recherche

Apprentissage de représentations

Apprentissage par renforcement

Modèles génératifs

Réseaux de neurones récurrents

Systèmes dynamiques

Théorie de l'information

Site web

Google Scholar

GitHub

Publications

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

Gaspard Lambrechts

Damien Ernst

Aditya Mahajan

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learni… (voir plus)ng paradigm. This paradigm leverages additional state information available at training time for faster learning. Although the proposed learning objectives are usually theoretically sound, these methods still lack a precise theoretical justification for their potential benefits. We propose such a justification for asymmetric actor-critic algorithms with linear function approximators by adapting a finite-time convergence analysis to this setting. The resulting finite-time bound reveals that the asymmetric critic eliminates error terms arising from aliasing in the agent state.

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

Gaspard Lambrechts

Damien Ernst

Aditya Mahajan

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

openreview.net