(she/they) Researcher @ Sapienza University of Rome. Interests: reinforcement learning, optimization, transport After 6pm: painting, photography, music, parties
Check out our newly published article "Solving the train dispatching problem via deep reinforcement learning", available online for a short period of time :)
https://t.co/dEdoDcf0V3
#Optrail#reinforcementlearning#rail#optimization#ai @ORMS_Elsevier
I am excited to announce that I will be organizing a special session on Distributed Computing in Bioinformatics and Computational Biology at the upcoming Conference on Computational Intelligence Methods for Bioinformatics & Biostatistics
https://t.co/Qjrq4IreeJ
The great competition between Deep Learning frameworks enters a new phase.
Now that Google's TensorFlow has lost to Meta's PyTorch, Google is internally switching to JAX.
NLP and offline RL are a perfect fit, enabling large language models to be trained to maximize rewards for tasks such as dialogue and text generation. We describe how ILQL can make this easy in our new paper: https://t.co/ssxXvihWit
Code: https://t.co/mrbFVX2Gar
Thread ->
Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks
https://t.co/JAnkdYkwIu
by Steffen Jung et al.
#LossFunction#ConvolutionalNeuralNetwork
Introducing #AlphaCode: a system that can compete at average human level in competitive coding competitions like @codeforces. An exciting leap in AI problem-solving capabilities, combining many advances in machine learning!
Read more: https://t.co/yaXfMWtEfe 1/
Did you know that some neural networks can be compressed without affecting their underlying models?
Some of the connections involved are at the 99th percentile of weight magnitude, all thanks to optimization! #orms
Come see our #NeurIPS2021 poster at 7:30 PM EST today!
Are you a master student/a PhD/a PostDoc/a young researcher in #orms? Have you sign up for the 6th @AIROYoung workshop already? No? Hurry up! 😊 the workshop will be held in Rome (🍝☀️) on 23-25 of February. As always, free of charge!
Read more here: https://t.co/tsRihJi1v2
[1/N] This work received an outstanding paper award at NeurIPS 2021!
To learn more about this work, please see https://t.co/RLOuconD1W. Some important links below.
Today we describe a collaboration with @TAE to improve fusion reactor performance by streamlining the optimization process, which helped to achieve longer stable plasma lifetimes, and we present research to better understand plasma behavior. Learn more at https://t.co/m7LHE5oapg
Marta Monaci, Valerio Agasucci, Giorgio Grani: An actor-critic algorithm with deep double recurrent agents to solve the job shop scheduling problem https://t.co/U4b9xntpFS https://t.co/A8Yf60XKEv