Alexandre Piché

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 19

Top Topics

Reinforcement Learning

Variance Reduction

Diffusion Models

Top Venues

Trans. Mach. Learn. Res.

ICLR (Workshop)

Publications

Alexandre Piché, Aristides Milios, Dzmitry Bahdanau, Chris Pal
LLMs can learn self-restraint through iterative self-reflection. CoRR (2024)
Christopher Beckham, Alexandre Piché, David Vázquez, Christopher Pal
Exploring validation metrics for offline model-based optimisation with diffusion models. Trans. Mach. Learn. Res. 2024 (2024)
Alexandre Piché, Valentin Thomas, Joseph Marino, Rafael Pardinas, Gian Maria Marconi, Christopher Pal, Mohammad Emtiyaz Khan
Bridging the Gap Between Target Networks and Functional Regularization. Trans. Mach. Learn. Res. 2023 (2023)
Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen, Alexandre Piché, Bart Dhoedt, Aaron C. Courville, Alexandre Lacoste
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels. ICML (2023)
Stephanie Long, Alexandre Piché, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin
Causal Discovery with Language Models as Imperfect Experts. CoRR (2023)
Stephanie Long, Tibor Schuster, Alexandre Piché
Can large language models build causal graphs? CoRR (2023)
Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen, Alexandre Piché, Bart Dhoedt, Aaron C. Courville, Alexandre Lacoste
Unsupervised Model-based Pre-training for Data-efficient Control from Pixels. CoRR (2022)
Alexandre Piché, Rafael Pardinas, David Vázquez, Igor Mordatch, Chris Pal
Implicit Offline Reinforcement Learning via Supervised Learning. CoRR (2022)
Christopher Beckham, Alexandre Piché, David Vázquez, Christopher Pal
Towards good validation metrics for generative models in offline model-based optimisation. CoRR (2022)
Alexandre Piché, Valentin Thomas, Joseph Marino, Rafael Pardinas, Gian Maria Marconi, Christopher Pal, Mohammad Emtiyaz Khan
Bridging the Gap Between Target Networks and Functional Regularization. CoRR (2022)
Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo, Yisong Yue
Iterative Amortized Policy Optimization. NeurIPS (2021)
Alexandre Piché, Joseph Marino, Gian Maria Marconi, Christopher Joseph Pal, Mohammad Emtiyaz Khan
Beyond Target Networks: Improving Deep Q-learning with Functional Regularization. CoRR (2021)
Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo, Yisong Yue
Iterative Amortized Policy Optimization. CoRR (2020)
Alexandre Piché, Valentin Thomas, Cyril Ibrahim, Yoshua Bengio, Chris Pal
Probabilistic Planning with Sequential Monte Carlo methods. ICLR (Poster) (2019)
Joshua Romoff, Alexandre Piché, Peter Henderson, Vincent François-Lavet, Joelle Pineau
Reward Estimation for Variance Reduction in Deep Reinforcement Learning. CoRR (2018)
Joshua Romoff, Peter Henderson, Alexandre Piché, Vincent François-Lavet, Joelle Pineau
Reward Estimation for Variance Reduction in Deep Reinforcement Learning. CoRL (2018)
Rémi Le Priol, Alexandre Piché, Simon Lacoste-Julien
Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields. UAI (2018)
Joshua Romoff, Alexandre Piché, Peter Henderson, Vincent François-Lavet, Joelle Pineau
Reward Estimation for Variance Reduction in Deep Reinforcement Learning. ICLR (Workshop) (2018)
Rémi Le Priol, Alexandre Piché, Simon Lacoste-Julien
Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields. CoRR (2017)