🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Congrats to my PhD student Adrien Alitaiga for winning Best Paper Award at the Exploration in RL Workshop at ICML19, "Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment"! Talk today, 11:30, Hall A. #ICML2019 #ERL19 Aaron Courville Michelle Cholodovskis Machado William Fedus

In 'Benchmarking Bonus-Based Exploration Methods in ALE' we find that when standardizing training duration, architecture, model capacity - new methods do not clearly improve over prior baselines Work led by Adrien Alitaiga which received ICML exp. workshop 2019 best paper award!

We're pleased to let you know that your submission, On Bonus Based Exploration Methods In The Arcade Learning Environment, has been accepted at #ICLR2020! openreview.net/forum?id=BJewl… This huge endeavor was led by Adrien Alitaiga. W/ William Fedus, Marc G. Bellemare & Aaron Courville. More👇🏼

At #ICML2021 and excited about RL? Come to the RL social this evening 5-7 PM PT! All levels of experience welcome, especially newcomers. We're lucky to have several RL experts confirmed attending -- a great opportunity to chat with them :) Join: icml.cc/virtual/2021/s…

🏆 BEST COOPERATIVE AI POSTER AWARD 🏆 Introducing Coordination in Concurrent Reinforcement Learning Congrats to Adrien Alitaiga, Aaron Courville and Marc G. Bellemare! Many thanks to our sponsor Cooperative AI Foundation.

Gather-Attend-Scatter (GATS), a novel module that combines pretrained foundation models operating at different rates into larger multimodal networks. Paper: arxiv.org/abs/2401.08525

Super simple code change to get value-based deep RL scale *much* better w/ big models across the board on Atari games, robotic manipulation w/ transformers, LLM + text games, & even Chess! Just use classification loss (i.e., cross entropy), not MSE!! arxiv.org/abs/2403.03950🧵⬇️

Framing regression as a classification has been “dark knowledge” for some time. We wanted to shed some light on this phenomenon in deep RL: Framing value-learning as a classification significantly improves performance and scalability in deep RL. But... not all classification

Grraaaaahh!! @tomlpr

Leaving tomorow for peru with Perunidad

La chose qui va le plus me manquer quand je partirai du Perou c'est le Inca Kola.

@ElmirOussama je suis tombe malade, je n'ai pas pu sortir hier et j'ai dormis de 15h à 9h30, tu as mieux a proposer?