Pierre-Luc Bacon

@pierrelux

Prof. at @UMontrealDIRO @MILAMontreal

Montreal

pierrelucbacon.com

Replies Reposts Media

Pierre-Luc Bacon
@pierrelux
Sep 26, 2025
Excited to share our new preprint on refrigerant discovery. It started as a bold idea brought by Anna Vartanyan @annadaneau, and thanks the amazing work of Adrien Goldszal, @diegocalanzone, Vincent Taboga, it became a reality.
arxiv.org
Discovery of Sustainable Refrigerants through Physics-Informed RL...
Most refrigerants currently used in air-conditioning systems, such as hydrofluorocarbons, are potent greenhouse gases and are being phased down. Large-scale molecular screening has been applied to...
1
Pierre-Luc Bacon
@pierrelux
Jan 28, 2024
🎉Congrats to Tianwei for his remarkable intuition and dedication. Our paper provides theoretical grounding for self-predictive RL and bridges to established theories on learning approximate information states in POMDPs.
Tianwei Ni
@twni2016
Jan 28, 2024
Replying to @twni2016
Our unification justifies *auxiliary tasks*. Training an encoder end-to-end for maximizing returns with the auxiliary task of learning ZP, as in SPR paper arxiv.org/abs/2007.05929, promises to learn self-predictive abstraction, also known as bisimulation and model-irrelevance.
1
Pierre-Luc Bacon
@pierrelux
Jan 24, 2024
🎉 Excited to share our new paper accepted at AISTATS 2024: "Maximum Entropy GFlowNets with Soft Q-Learning" 🔗 arxiv.org/abs/2312.14331. Kudos to Sobhan Mohammadpour for his stellar work in his MSc thesis!
arxiv.org
Maximum entropy GFlowNets with soft Q-learning
Generative Flow Networks (GFNs) have emerged as a powerful tool for sampling discrete objects from unnormalized distributions, offering a scalable alternative to Markov Chain Monte Carlo (MCMC)...
1
Pierre-Luc Bacon
@pierrelux
Jan 21, 2024
Congrats to Mahan, who is finishing his Master's thesis in beauty with this second paper.
Mahan Fathi
@MahanFathi
Jan 17, 2024
Course Correcting Koopman Representations Accepted at #ICLR2024! We identify problems with unrolling in imagination and propose an unconventional, simple, yet effective solution: periodically "𝒓𝒆𝒆𝒏𝒄𝒐𝒅𝒊𝒏𝒈" the latent. 📄 arxiv.org/abs/2310.15386 @GoogleDeepMind 1/🧵
Pierre-Luc Bacon
@pierrelux
Dec 11, 2023
🌟 Proud of @MahanFathi's msc work in collaboration with @GoogleDeepMind! Block-State Transformer elegantly combine SSM's long-range efficiency and Transformer's NLP advantage. 🚀 BST outperforms in language modeling and scales easily. Don't miss their poster at #NeurIPS2023
Mahan Fathi
@MahanFathi
Dec 9, 2023
Why not get the best of both worlds by combining SSMs and Transformers? Excited to share our work at #NeurIPS2023: "Block-State Transformers." BST hits new highs in long-range language modeling and LRA tasks. paper: arxiv.org/abs/2306.09539 1/