This year, ICML received over 12,000 submissions, and only 313 were selected for spotlight presentations – placing our paper in the top 2.6% most highly recommended by the program committee. I’m proud to see Pedro’s work recognized at this level!
Excited to share that our paper “The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes” has been accepted as a spotlight poster at ICML 2025! ICML is one of the top-tier conferences in AI and M L (CORE A* and featured in CSRankings).
Huge congratulations to @ppspedrosantos, our PhD student (also advised by @facsmelo) and first author of this work! His dedication and deep thinking were fundamental to this achievement.
Wishing you and your loved ones a joyful holiday season filled with peace, love, and new opportunities. Let’s make 2025 even brighter together!
Happy Holidays and a Happy New Year!
Excited to announce that we had three papers accepted at AAMAS, a top-tier AI conference (CORE A*). This includes two full papers and one extended abstract. Congratulations to my amazing co-authors Guilherme Varela, Fábio Vital, and Francisco Melo for this fantastic achievement!
Celebrando a IA na @pucriooficial: Competição de Carros Autônomos!
Realizamos uma emocionante competição de carros autônomos como projeto da disciplina de Deep Reinforcement Learning do @dipucrio
Parabéns a todos os envolvidos pelo esforço e criatividade ao longo do semestre!
Excited to Share Our First Test of an Autonomous Vehicle Using Deep Reinforcement Learning!
As part of the final assignment for my graduate course at the @dipucrio at @pucriooficial, my students and I have been testing an autonomous vehicle powered by Deep RL.
After seeing some intriguing posts from friends recently, I decided to try something new and asked ChatGPT to create an image based on what this AI knows about me. Cool! #AI#ChatGPT#Innovation
This week, I am attending the Trust and Influence Program Review hosted by the Air Force Office of Scientific Research in Dayton, OH. It’s a great opportunity to present our research from the Trustworthy Ad Hoc Teamwork project and to connect with so many amazing researchers.
I'm thrilled to announce that I'll be a panelist at the "Inova IA" event next Tuesday! Don't miss this event—it's going to be an exciting discussion on the future of AI! @riosoft_oficial
https://t.co/xR6eb8agUC
So cool! It's incredible to see how the integration of Large Language Models (LLMs) and Reinforcement Learning is paving the way for groundbreaking AI advancements.
https://t.co/LEO5RUFaCq
TV PUC-Rio prepared a short video (in Portuguese) about the ECOA Conecta event with Hassan Sawaf from @aixplain. It was a fantastic opportunity for students to engage with cutting-edge AI discussions. Moderation: Prof. Alberto Sardinha, @dipucrio
https://t.co/xQTXwifhL5
I am excited to share that our paper, 'HOTSPOT: An Ad Hoc Teamwork Platform for Mixed Human-Robot Teams,' has been accepted for publication in PLoS One, a Q1 journal in ISI, Scopus, and Scimago! #MachineLearning#AI#Research
I participated in the ECOA Conecta event at @pucriooficial with Hassan Sawaf, CEO of @aixplain . Thank you, Hassan, for sharing your inspirational insights on the AI landscape!
I am excited to share that our paper, 'HOTSPOT: An Ad Hoc Teamwork Platform for Mixed Human-Robot Teams,' has been accepted for publication in PLoS One, a Q1 journal in ISI, Scopus, and Scimago! #MachineLearning#AI#Research
Thrilled to announce that our paper titled 'The Impact of Data Distribution on Q-learning with Function Approximation' has been accepted for publication in Machine Learning, a prestigious Q1 journal in ISI, Scopus, and Scimago! #MachineLearning#AI#Research
I am happy to announce that I received the "Excellence in Teaching Award" for my course "Autonomous Agents and Multiagent Systems" during my last year at IST. Thank you to all my students at IST!