Alessio Russo
@alessiorusso.bsky.social
Postdoc at Boston University with Aldo Pacchiano (PLAIA Lab plaia.ai). Interested in RL, Bandit problems and Adaptive Control.
Website: alessiorusso.net
Website: alessiorusso.net
Thanks again to @aldopacchiano.bsky.social and #BostonUniversity for this opportunity! #reinforcementlearning #rl
November 27, 2025 at 1:24 PM
Thanks again to @aldopacchiano.bsky.social and #BostonUniversity for this opportunity! #reinforcementlearning #rl
PS: In the local timezone the poster session will be at 4:30 p.m. PST
November 25, 2025 at 3:06 PM
PS: In the local timezone the poster session will be at 4:30 p.m. PST
With Daniele Foffano & Alexandre Proutiere. Happy to meet in SD!
Paper:
Adversarial Diffusion for Robust Reinforcement Learning
Robustness to modeling errors and uncertainties remains a central challenge in reinforcement learning (RL). In this work, we address this challenge by leveraging diffusion models to train robust...
arxiv.org
November 25, 2025 at 2:57 PM
With Daniele Foffano & Alexandre Proutiere. Happy to meet in SD!
Paper:
AD-RRL uses diffusion-guided adversarial trajectories to train robust policies using a CVaR objective.
It's a Dyna-style loop: collect rollouts; train a diffusion model; adversarially guide sampling to produce worst-case trajectories; train the RL agent on this data; iterate.
It's a Dyna-style loop: collect rollouts; train a diffusion model; adversarially guide sampling to produce worst-case trajectories; train the RL agent on this data; iterate.
November 25, 2025 at 2:57 PM
AD-RRL uses diffusion-guided adversarial trajectories to train robust policies using a CVaR objective.
It's a Dyna-style loop: collect rollouts; train a diffusion model; adversarially guide sampling to produce worst-case trajectories; train the RL agent on this data; iterate.
It's a Dyna-style loop: collect rollouts; train a diffusion model; adversarially guide sampling to produce worst-case trajectories; train the RL agent on this data; iterate.
In each review process a reviewer usually reviews 2 to 5 papers. For each paper reviewed they obtain a score from the AC of that paper, normalized by the pattern of scores of that AC. If during a PhD you review 20-30 papers, that should give a roughly good estimate of the quality of your reviews.
November 19, 2025 at 1:37 PM
In each review process a reviewer usually reviews 2 to 5 papers. For each paper reviewed they obtain a score from the AC of that paper, normalized by the pattern of scores of that AC. If during a PhD you review 20-30 papers, that should give a roughly good estimate of the quality of your reviews.
How do we do that? This is not the place to brainstorm, but I applaud the system of #ICLR to make reviews public, this is a first step, and in my opinion, this should be the standard. What do we need to hide? Furthermore, I will throw a simple idea: introduce an ELO system for reviewers.
November 19, 2025 at 1:37 PM
How do we do that? This is not the place to brainstorm, but I applaud the system of #ICLR to make reviews public, this is a first step, and in my opinion, this should be the standard. What do we need to hide? Furthermore, I will throw a simple idea: introduce an ELO system for reviewers.
LLMs should be intended to augment your work skills, to empower yourself and be more productive.
What we lack is a form of accountability. It is irresponsible not to make reviewer accountable for reviews of poor quality with wrong/false statements.
What we lack is a form of accountability. It is irresponsible not to make reviewer accountable for reviews of poor quality with wrong/false statements.
November 19, 2025 at 1:37 PM
LLMs should be intended to augment your work skills, to empower yourself and be more productive.
What we lack is a form of accountability. It is irresponsible not to make reviewer accountable for reviews of poor quality with wrong/false statements.
What we lack is a form of accountability. It is irresponsible not to make reviewer accountable for reviews of poor quality with wrong/false statements.
I don't see a collapse of the review process. We won’t see a hard technical failure. People will simply use LLMs more and more to deal with the larger and larger amount of work. Note that I don't oppose the use of LLMs.
November 19, 2025 at 1:37 PM
I don't see a collapse of the review process. We won’t see a hard technical failure. People will simply use LLMs more and more to deal with the larger and larger amount of work. Note that I don't oppose the use of LLMs.
Some people are waiting for the "inevitable" collapse of the review process. Even if a collapse happens (not even clear what we mean by collapse here), if we don't take action to prevent this sort of problem from happening again, then it will eventually happen again.
November 19, 2025 at 1:37 PM
Some people are waiting for the "inevitable" collapse of the review process. Even if a collapse happens (not even clear what we mean by collapse here), if we don't take action to prevent this sort of problem from happening again, then it will eventually happen again.
This news is not new. I'm surprised by the lack of actions of chairs who, supposedly, should be doing something, but instead I see the same pattern conference after conference.
November 19, 2025 at 1:37 PM
This news is not new. I'm surprised by the lack of actions of chairs who, supposedly, should be doing something, but instead I see the same pattern conference after conference.
Registration form forms.gle/ohC8KJPPbBt6...
Course on Pure Exploration in RL and Active Sequential Hypothesis Testing- Expression of Interest
Dear all, I'm Alessio Russo, a Postdoc at BU (PLAIA group).
I’m planning a PhD-level short course on sequential hypothesis testing and pure exploration. See also the website for more information ht...
forms.gle
October 30, 2025 at 11:26 AM
Registration form forms.gle/ohC8KJPPbBt6...
In this work we studied the sample complexity of pure exploration in an online learning problem with a general unknown stochastic feedback graph. A setting that was not well studied before in literature.
March 12, 2025 at 1:58 PM
In this work we studied the sample complexity of pure exploration in an online learning problem with a general unknown stochastic feedback graph. A setting that was not well studied before in literature.