π’ Iβm looking for ππ¨π¬πππ¨ππ¬ to join my team working on π«ππ’π§ππ¨π«πππ¦ππ§π π₯πππ«π§π’π§π !
π§ Theory- or experiment-oriented profiles
π° Funded by π ππ2 Starting Grant (Italian ERC equivalent)
Details: https://t.co/32VwgR13gU
Please share!
π Congratulations to @marcomussi95 for winning the prestigious Dimitris N. Chorafas Prize for his PhD thesis βOnline Learning Methods for Pricing and Advertising.β A remarkable achievement! π
At #EWRL2025 in TΓΌbingen, @alberto_metelli and @papinimat presented their contributed talks - great insights on inverse RL and policy gradients shared with the community!
We've extended the deadline for our workshop's calls for papers/ideas! Submit your work by August 29 AoE. Instructions on the website: https://t.co/j7YBIHen0Q
The OpenReview link for our calls (for papers and ideas) is available, submit here: https://t.co/eqkSQFicmx
We look forward to receiving your submissions!
(3/3) @montenegronwski , @marcomussi95 , @papinimat@alberto_metelli will present a new framework explaining why dynamically tuning exploration in PG methods works and guarantees for a common practical approach.
πWest Exhibition Hall B2-B3#W-808β¨π Thu 17Jul,4:30 PMβ7:00 PM PDT
π¨ Thursdayβs Poster @ #ICML2025 π¨
Tomorrow, we will present three papers, (1) "Learning Utilities from Demonstrations in MDPsβ, (2) "Sleeping Reinforcement Learning", (3) "Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity"!
The @rl3polimi group will be at #ICML2025 with 6 papers, including 1 position paper! π
Weβll be sharing details about each contribution in the coming daysβstay tuned!
Looking forward to connecting in Vancouver π¨π¦
(2/3)@simonedrago_ ,@marcomussi95 , and @alberto_metelli will present a new RL paradigm for settings where available actions change over time, explore the regret minimization problem and its challenges.
πWest Exhibition Hall B2-B3 #W-707β¨π Thu 17 Jul, 11:00 AMβ1:30 PM PDT
@vincenz94, @RiccZamboni and @mirco_mutti will give an original take on how to make the best of parallel data collection for RL, how to enforce behavioral diversity and what this leads to in downstream tasks.
πWest Exhibition Hall B2-B3 #W-601β¨π Wed 16 Jul,4:30 PMβ7:00 PM PDT
π¨ Wednesdayβs Poster @ #ICML2025 π¨
Tomorrow, we will present one paper βEnhancing Diversity in Parallel Agents: A Maximum Exploration Storyβ!
The @rl3polimi group will be at #ICML2025 with 6 papers, including 1 position paper! π
Weβll be sharing details about each contribution in the coming daysβstay tuned!
Looking forward to connecting in Vancouver π¨π¦
(2/2) Later, @simonedrago_,@marcomussi95,@alberto_metelli will present a theoretical framework that bridges preference feedback, utilities, and rewards, laying the groundwork for RL from human preferences.
πWest Exhibition Hall B2-B3 #W-1008β¨π Tue 15 Jul, 4:30β7:00 PM PDT
π¨Tuesdayβs Poster @ #ICML2025π¨
Tomorrow, we will present two papers: "Position: Constants are Critical in Regret Bounds for Reinforcement Learning"
(1) & βTowards Theoretical Understanding of Sequential Decision Making with Preference Feedback"(2)!
The @rl3polimi group will be at #ICML2025 with 6 papers, including 1 position paper! π
Weβll be sharing details about each contribution in the coming daysβstay tuned!
Looking forward to connecting in Vancouver π¨π¦
(1/2)@simonedrago_ ,@marcomussi95,@alberto_metelli will challenge the obsession with asymptotics in RL theory, arguing that *constants matter*.
πEast Exhibition Hall A-B #E-503β¨π Tue 15 Jul, 11:00 AMβ1:30 PM PDT
The @rl3polimi group will be at #ICML2025 with 6 papers, including 1 position paper! π
Weβll be sharing details about each contribution in the coming daysβstay tuned!
Looking forward to connecting in Vancouver π¨π¦
Four projects of @polimi have been awarded funding under the Fondo Italiano per la Scienza, the fund for basic research set up by @mur_gov_.
Congratulations to Giorgio Besagni, @fiorito_daniele, @MxgTeo and @alberto_metelli!
For more information: https://t.co/L0EqlStVVg
#PolimiResearch
π¨ 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.
π Apply by May 31, 2025
π https://t.co/32VwgR13gU
π Spread the word!
Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! https://t.co/GrDfgzW1fL