colletti.r_
riccardo@berkeley:~/portfolio 
$ whoami
Hi, I'm Riccardo. Yes, another engineer — but
(mostly) fun at parties.

$ cat ./about.txt
I studied in Milan and now I'm in Berkeley.
Translation: I've moved around a lot, collected
too many student IDs, and somehow still haven't
figured out how to cook pasta properly (yes,
I know, shame on me — I'm Italian).

$ ls ./now/
multi_agent_rl_drift/   dispatch_optim/   drift_happens/

$ echo $LOOKING_FOR
AI / ML / RL · PM · Growth · Product Marketing
— places where data and gut both get to talk.

$ echo $INTERESTS
🎾 padel  ·  🏃 running  ·  ⚽ Inter Milan  ·  ✈️ travel

$ _
// 01

about

/* who, what, why */

Hi, I'm Riccardo. I work on AI, machine learning, and deep reinforcement learning, which mostly means teaching computers to figure things out, then arguing with them when they don't. I'm finishing my MEng in EECS at UC Berkeley, after a Master's at Bocconi and an engineering degree at Politecnico di Torino. Three countries, three degrees, and probably too much espresso.

Sports taught me discipline and how to take feedback without taking it personally. Engineering taught me rigor. Business taught me that rigor, on its own, is rarely enough. Volunteering reminded me that not everything is about moving faster, and that sometimes stopping to pay attention is part of doing meaningful work.

When something doesn't make sense or refuses to work, I tend to obsess over it until it gives in. Everything else, less so. I value curiosity, honesty, and a real sense of humor, especially around smart, opinionated people who actually care about what they're building.

// tech.stack
lang python · c/c++ · sql · matlab · ts
ml pytorch · jax · scikit-learn · numpy · pandas
data sql · excel · google sheets
infra docker · aws · postgres
// riccardo.stack
fuel espresso · pasta · gelato
training padel · running · swimming
team Inter Milan — for the highs, the lows, and the swearing in between
moves turin → milan → ireland → milan → berkeley
langs italian · english · latin (rusty) · french (nodding politely)
volunteering OFTAL · AGAPE Onlus
// 02

current research

/* what I'm building right now */
~/research/hydramarl.md 2026 · neurips submission

HydraMARL

A foundational study of parameter sharing in cooperative multi-agent reinforcement learning. Existing methods entangle sharing with auxiliary machinery (clustering, adapters, diversity bonuses), confounding what's actually driving performance. HydraMARL disentangles them on a minimal shared-backbone + per-agent-head architecture, and gives the first principled characterization of the speed-vs-specialization spectrum in cooperative MARL.

When many AI agents learn together, parts of their neural networks can be shared. We isolate how much sharing actually helps, and expose the real trade-off between learning fast and learning to specialize.

  • multi-agent rl
  • parameter sharing
  • neurips '26
~/research/klip_ppo.md 2026 · neurips submission

KLip-PPO

A theoretical unification of PPO-Clip and PPO-KL, the two dominant variants of the most widely used policy-gradient algorithm in modern reinforcement learning. We prove a per-sample equivalence: clipping carries an implicit KL penalty hidden in its objective. The result collapses what was treated as a divide in the field into a single design space, and uncovers a principled family of generalizations of PPO.

PPO is the most widely used algorithm in modern RL. Its two main variants were thought to be different ideas. We prove they're mathematically the same thing, and unify how the field thinks about them.

  • rl theory
  • ppo
  • policy optimization
~/research/demand.md 2026 · framework

DEMAND / no-steady-state

A research framework for multi-agent reinforcement learning under non-stationary demand, targeting fleet dispatch problems in delivery, ride-hailing, and logistics. The platform models the full operational stack (order matching, routing, courier repositioning) under realistic exogenous drift, with plug-and-play integration of 15+ RL algorithms (PPO, SAC, multi-agent variants, classical heuristics). Designed for the controlled drift studies that current MARL benchmarks cannot support.

A research platform for studying how AI dispatch systems (food delivery, ride-hailing) hold up when demand keeps changing. Full simulation pipeline with many algorithms wired in.

  • multi-agent rl
  • simulation
  • operations
~/capstone/no_free_lunch.md 2025 · capstone · informs/meituan

No Free Lunch for Food Delivery

A multi-objective study of courier-assignment policies on real Meituan delivery data, where customer latency, courier earnings, platform margin, and restaurant reliability fundamentally conflict. We benchmark classical heuristics and modern reinforcement learning, then propose PRISM: a hybrid architecture combining learned cost prediction, RL, and constraint optimization that treats Pareto trade-offs as first-class objectives instead of collapsing them into a scalar reward.

In food delivery, customers, couriers, platforms, and restaurants all want different things from the same decision. Built on real Meituan data, PRISM treats those trade-offs as first-class instead of pretending they aren't there.

  • operations research
  • multi-objective
  • real data
~/research/drift_happens.md 2025 · research · drift-happens.org ↗

Drift Happens

A large-scale empirical study of how neural architectures hold up under temporal distribution shift, spanning image, text, and tabular benchmarks. We show that domain-matched inductive biases (convolutional priors for vision, etc.) are first-order determinants of long-horizon robustness — generic architectures collapse under realistic drift, while structured ones degrade gracefully. The result reframes architecture selection itself as a temporal-robustness prior, not just a static performance choice.

AI models tend to lose accuracy as the world changes around them. We tested many neural networks over time and found the architecture you pick is also a bet on how the future will look.

  • neural nets
  • distribution shift
  • empirical
~/robotics/hold_your_plate.md 2025 · robotics · holdurpla7e.org ↗

Hold Your Plate

Real-time ball-on-plate stabilization on a UR7e collaborative arm, with ArUco vision tracking through an Intel RealSense camera, orchestrated on a full ROS 2 stack and a MuJoCo simulation pipeline. The system compares three controllers: a hand-tuned PID, an MPC on the linearized dynamics, and a residual learning approach that augments the PID with a small PPO policy trained under domain randomization (varied mass, friction, sensing delay) — pairing the reliability of model-based control with learned robustness to unmodeled effects.

A UR7e robotic arm balancing a ball on a tilting plate, with a camera tracking it in real time. Compares three controllers (classical, model-based, and learned) on a ROS 2 stack.

  • ros 2
  • residual rl
  • ur7e
  • mujoco
  • vision
// 03

snapshots

/* a portrait of my life · the [EE] ones hide easter eggs */
~/life/quadri/ 5 frames · easter eggs inside
01quadro_01.jpgEE
02quadro_02.jpgEE
03quadro_03.jpgEE
04quadro_04.jpgEE
05quadro_05.jpgEE
~/life/school/ 3 frames
01bocconi.jpg
02berkeley.jpg
03party.jpg
~/life/sports/ 4 frames
01padel.jpg
02running.jpg
03ski_italy.jpg
04warriors.jpg
~/life/travel/ 6 frames
01cambodia.jpg
02finland.jpg
03toronto.jpg
04golden_gate.jpg
05hollywood.jpg
06grand_canyon.jpg
// 04

cv

/* timeline */

# education

  1. Aug 2025 → May 2026
    UC Berkeley · Berkeley, CA GPA 4.0 / 4.0
    MEng in Electrical Engineering & Computer Sciences Statistical learning theory, machine learning, deep reinforcement learning (policy gradients, actor–critic, model-based), optimization. Fung Excellence Scholar — Berkeley Engineering merit award for top MEng students.
  2. 2024 → May 2025
    Bocconi University · Milan, IT 110L / 110 (cum laude)
    MSc in Marketing Management & Communication (MiMeC) Valedictorian — best overall student of the cohort. Merit-based scholarship. Quantitative program focused on analytics, consumer behavior, pricing strategy, and data-informed decision-making.
  3. Aug 2017 → May 2021
    Politecnico di Torino · Turin, IT 110L / 110 (cum laude)
    BSc in Electronic & Communications Engineering Top of class — English-taught ICT engineering program. Honors track (Intraprendenti — Young Talents Program): top 200 students university-wide. Thesis on Digital PLL simulation.

# experience

  1. Jan → Jul 2025
    Lenovo · Milan, IT
    Marketing Specialist · CRM Digital Services CRM and marketing analytics: customer segmentation, campaign analysis, CRM data exploration. Translated analytical insights into marketing and growth inputs inside a global, data-intensive corporate environment.
  2. 2021 → 2025
    Rialco S.R.L. · Milan, IT
    CEO / Product Manager / Growth Manager Owned strategic direction and P&L of a digital consulting firm. Led discovery → ship for digital products (web, e-commerce, internal tooling). Ran acquisition and conversion across SEO, paid, and social — defining KPIs and using analytics to prioritize what moved the funnel.
  3. Jan → Jul 2020
    Biesse Sistemi S.R.L. · Nizza Monferrato, IT
    Intern · Software Development Voice-controlled application for automated taxi booking — application logic and system integration alongside a senior software developer.

# awards & scholarships

  1. 2025
    Fung Excellence Scholarship · UC Berkeley Awarded by Berkeley Engineering to top MEng candidates.
  2. 2025
    Valedictorian + Merit-Based Scholarship · Bocconi University Best overall student of the cohort.
  3. 2017 → 2021
    Intraprendenti — Young Talents Program · Politecnico di Torino Top 200 students university-wide.

$ open cv.pdf ↗ · resume.pdf ↗