📢 I’m looking for 𝐏𝐨𝐬𝐭𝐃𝐨𝐜𝐬 to join my team working on 𝐫𝐞𝐢𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠!
🧠 Theory- or experiment-oriented profiles
💰 Funded by 𝐅𝐈𝐒2 Starting Grant (Italian ERC equivalent)
Details: https://t.co/32VwgR13gU
Please share!
🚀 Congratulations to @marcomussi95 for winning the prestigious Dimitris N. Chorafas Prize for his PhD thesis “Online Learning Methods for Pricing and Advertising.” A remarkable achievement! 🎉
🚨 We're hiring!
We are looking for postdocs and PhD students to join the Reinforcement Learning group at @polimi in Fall 2025 to work on the theory and practice of human feedback in RL.
📅 Apply by May 31, 2025
🔗 https://t.co/32VwgR13gU
🔁 Spread the word!
📣 Can we optimally learn in Kernelized Bandits with Bernoulli rewards? In our open problem, we discuss possible insights and the questions we have to address to solve this problem.
🗓️ Fri, Jul 26, 13:25 - Poster Session 1 of the ARLET Workshop at #ICML2024
🔮Now you can learn deterministic policies with theoretical guarantees🔮
If you missed the @rl3polimi’s spotlight paper at @icmlconf, here you are:
https://t.co/iV0Xa8psLl
📣 How can we learn sequential decision problems where actions impact specific system parts with intermediate effects? In our #ICML2024 paper, we introduce factored reward bandits and provide regret lower bounds and tight algorithms.
🗓️ Wed, Jul 24, 13:30 -- Poster Session 4
📣 What’s between rested and restless bandits? In our #ICML2024 paper, we propose a novel generalization of rested and restless bandits where the evolution of the arms' expected rewards is governed by a graph defined over the arms.
🗓️ Tue, Jul 23, 13:30 - Poster Session 2
📣 How can we achieve global last-iterate convergence to the best deterministic policy? Our spotlight paper at #ICML2024 dives into this challenge using parameter-based and action-based stochastic policy gradients.
🗓️ Tue, Jul 23, 13:30 - Poster Session 2
🚀 The RL3 team is thrilled to announce that we'll be at
@icmlconf with 7 accepted papers (2 spotlights)! 🎉We're eager to share our research with the community. Stay tuned for more details on our papers in the coming days. #RL3#ReinforcementLearning#ICML2024
🚀 Welcome to RL3 - Real Life Reinforcement Learning Research Lab! We're a pioneering research group of AIRLab - Politecnico di Milano, dedicated to advancing reinforcement learning algorithms and applications. Follow us for the latest in #ReinforcementLearning! #RL3
But seriously folks, this a short and juicy tirade in which I say:
(0) there will be superhuman AI in the future
(1) they will be under our control
(2) they will not dominate us nor kill us
(3) they will mediate all of our interactions with the digital world
(4) hence, they will need to be open platforms so that everyone can contribute to training and tuning them.
Our paper "Dynamical Linear Bandits" will be presented tomorrow as a poster at #ICML2023 by me, @alberto_metelli and Marcello Restelli. Come and visit poster #400 at 2pm - Exhibit Hall 1!
https://t.co/P526VDLykl
📢 Excited to share that our group has 3 accepted papers at #ICML2023! A big thanks to my amazing collaborators: Filippo Lazzati, @marcomussi95, Riccardo Poiani, and Marcello Restelli.
At the CFOL workshop of #ICML2022, @95markm and I will present "Dynamical Linear Bandits for Long-Lasting Vanishing Rewards". In this paper, we propose a novel bandit framework with a hidden state to model delayed and cumulated effects of actions. Visit our poster (Room 314-315)!
We are excited to announce the 15th European Workshop on Reinforcement Learning #EWRL2022 that will be a physical event hosted by @polimi on 19-21 September in Milan! The #CFP is finally out at https://t.co/rnRO23FuUy. Join us to discuss the latest advancements in #RL!
Thread su come valutare la credibilità delle fonti in materia medica/biologica. Dire che una cosa è stata pubblicata e riportare il link dell’articolo non è sufficiente. Bisognerebbe anche leggerlo (dove il 90% della gente si ferma) e capire su cosa si basa.