Sign in

Aldo Pacchiano

@aldopacchiano.bsky.social
181 followers 73 following 13 posts

AI research at Broad Institute and Boston University. Reinforcement Learning / Bandits / Experiment Design Mexicano 🇲🇽

PostsRepliesMedia
Aldo Pacchiano @aldopacchiano.bsky.social · 03/05/2025
Our work "On the Hardness of Bandit Learning" co-authored with Nataly Brukhim, Miro Dudik and Robert Schapire got into COLT 2025!
060
Aldo Pacchiano @aldopacchiano.bsky.social · 02/05/2025
Three works accepted to ICML: 1. Multiple-policy Evaluation via Density Estimation - led by PhD student Yilei Chen, joint with Ioannis Paschalidis. 2. Adaptive Exploration for Multi-Reward Multi-Policy Evaluation - led by Alessio Russo. (1/2)
120
Aldo Pacchiano @aldopacchiano.bsky.social · 12/03/2025
New paper “Pure Exploration with Feedback Graphs” with BU postdoc Alessio Russo @alessiorusso.bsky.social and BU PhD student Yichen Song. Accepted for oral presentation @ AISTATS 2025.
030
Aldo Pacchiano @aldopacchiano.bsky.social · 30/01/2025
[1/5] Happy to share a bit about 3 papers accepted into ICLR 2025 “Second Order Bounds for Contextual Bandits with Function Approximation” Authored by me “A Theoretical Framework for Partially-Observed Reward States in RLHF” with Chinmaya Kausik, Mirco Mutti and Ambuj Tewari
120
Reposted by Aldo Pacchiano
Jack Parker-Holder @jparkerholder.bsky.social · 04/12/2024
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
1523461
Aldo Pacchiano @aldopacchiano.bsky.social · 04/12/2024
It is great to see the Decision Pretrained Transformer used in creative ways: ""HVAC-DPT: A Decision Pretrained Transformer for HVAC Control""! arxiv.org/pdf/2411.19746
arxiv.org
040
Reposted by Aldo Pacchiano
Jakob Foerster @jfoerst.bsky.social · 29/11/2024
🚨 PSA 🚨 Deadline to apply for your dream Phd in ML @FLAIR_Ox is coming up on the 2nd of December AOE. We work on compute-only scaling of LLMs, (meta/multi-agent) RL at the Hyperscale, Human-AI coordination, opponent-shaping for vaccine design, GenAI for finance & much more..
ox.ac.uk
DPhil in Engineering Science | University of Oxford
About the courseThe DPhil in Engineering Science will offer you the opportunity to develop in-depth knowledge, understanding and expertise in your chosen field of engineering research. To support
1163
Reposted by Aldo Pacchiano
Jeff Clune @jeffclune.com · 19/11/2024
The secret to doing good research is always to be a little underemployed. You waste years by not being able to waste hours. - Amos Tversky
0383
Aldo Pacchiano @aldopacchiano.bsky.social · 11/11/2024
I have just opened a profile here!
010