KCommand
Esc
↑↓Navigate Select 7 sections · 8 projects
Initializing portfolio00
Dario Leonardo Arcan
--:--:--CET · Veneto, IT ◆ Dario Leonardo Arcan ◆ Portfolio / Vol. 06 / MMXXVI

Always learning, always building.

$

World-ranked across five competitive titles. Now I channel that same obsessive pattern recognition into AI systems, reinforcement learning, and data science — building intelligent tools with the same intensity I used to reach the top.

5+
Games / World-Ranked
8
Shipped Projects
<1%
Global Percentile
24
Years Old
01IdentityWho I Am
The same mind that reached world rankings in competitive gaming now builds systems that think.
D·A
Dario Leonardo Arcan BSc AI & Data Science / H-FARM College

Most people treat gaming as entertainment. I treated it as a laboratory for decision-making under uncertainty — reading opponents, optimizing strategies in real time, finding edges invisible to everyone else. That's what took me to the Hearthstone Master Tour, to European and global leaderboards across multiple titles.

That cognitive toolkit doesn't disappear when you switch domains. It transfers directly into reinforcement learning, probabilistic modeling, and system design. Every project I ship carries the same intensity: find the optimal solution, execute precisely, iterate relentlessly.

5+
Games, World-Ranked
8+
Shipped Projects
RL
Core Focus
24
Years Old
02Competitive RecordProof of Pattern
A decade of reading systems, finding hidden structure, and exploiting it faster than anyone else.
Every rank below was earned at the highest tier of play — peak global or continental position. Not flukes. Repeatable performance under pressure.
MT
Hearthstone
World Championship
Qualified and competed at the Hearthstone Master Tour 2021 — Blizzard's premier global competition. Thousands of entrants, one stage.
2021
#2
Squad Busters
World  ·  Italy
Peaked at #2 globally and #2 in Italy in Supercell's real-time strategy brawler. Rapid decision-making and adaptive strategy under chaotic conditions.
2024
#3
Mo.Co
World
Peaked at #3 in the world. Pure mechanical precision combined with strategic depth — consistent top-tier performance from day one.
2025
#16
Teamfight Tactics
Europe  ·  #3 Italy
Top 16 in Europe in Riot Games' auto-battler. Economy management, probabilistic item optimization, and real-time composition pivoting — the closest any game gets to applied statistics.
2022
<1%
Cross-Game
Global  ·  Multi-Title
Consistently ranked in the top <1% globally across every competitive title I've touched. The transferable skill isn't game-specific — it's decoding systems faster than anyone else.
Ongoing
Why this matters for AI Competitive gaming at this level is applied decision theory — opponent modeling, expected value calculation, real-time Bayesian updating, and strategy under incomplete information. These are the same primitives that power reinforcement learning and intelligent systems. The instinct to find structure in noise doesn't come from a textbook.
03Selected Work2023 — 2026
01 / 08
Adaptive AI
Coco
An AI companion that doesn't just respond — it adapts emotionally. Coco runs a Finite State Machine with 6 mood states that shift based on conversation context, time patterns, and user behavior history.
Architecture — Three-tier memory (short-term buffer → session context → long-term persistence). Hybrid LLM routing with fallback chain: Claude API → OpenAI → local mock. Strategy, Observer, State, Repository design patterns. 38/38 unit tests passing.
Python FSM Claude API Design Patterns
02 / 08
Reinforcement Learning
RL Mario Agent
A PPO agent trained entirely from raw pixel input to beat Super Mario Bros World 1-1. No hand-crafted features, no human demonstrations — just a neural network learning through trial and error on 240×256 RGB frames.
Pipeline — Grayscale + 84×84 resize + 4-frame stack → CNN feature extractor → PPO policy with entropy bonus. Trained on RTX 5070 (Blackwell sm_120, required PyTorch nightly cu128). Diagnosed policy collapse via LR scheduling and entropy coefficient tuning. ~60% completion rate.
PyTorch PPO Computer Vision CUDA
03 / 08
Swarm Robotics
NECTAR
A precision agriculture platform built around a mother drone + micro-drone swarm architecture. Each micro-drone handles a specialized task — seeding, pollination monitoring, or targeted pesticide application.
Concept — Bio-inspired swarm coordination with task allocation algorithms, GPS waypoint navigation, real-time sensor feedback. Developed for a robotics hackathon (3-min pitch, 30 groups). Delivered a complete pitch package including business plan and market analysis.
Swarm Robotics Precision Ag Pitch
04 / 08
Game Theory
CINQUE
A zero-luck 1v1 strategy game inspired by the Colonel Blotto problem. Two players simultaneously allocate a 100-point budget across 5 lanes with asymmetric values. Pure cognition — no dice, no draws, no RNG.
Stack — React Native + Expo frontend, Firebase Realtime Database for synchronous multiplayer state. Commit-reveal anti-cheat — both players submit encrypted allocations before either is revealed. Clean architecture at cinque-fresh.
React Native Expo Firebase Game Theory
05 / 08
Game Development
FOSSALTA77
A cyberpunk-themed multiplayer card game — designed, built, and deployed as a single HTML file. 20 unique cards with distinct mechanics, cyberpunk visual identity, and real-time multiplayer through Firebase.
Shipped — Firebase Realtime Database for game state sync, Firebase Hosting for deployment (free tier). Entire game logic, UI, and styling in one self-contained file. Card balance designed through iterative playtesting. Live and playable.
Vanilla JS Firebase Game Design Shipped
06 / 08
Optimization
LDM-Optimizer
A 3D bin-packing algorithm that minimizes Loading Meters in semi-trailer trucks. Took over a legacy system and rewrote the core packing logic from scratch in TypeScript.
Algorithm — Row-First placement combined with Guillotine residual fill and Simulated Annealing metaheuristic. Delivered as a drop-in REST endpoint replacement with full ARCHITECTURE.md documentation. Handles weight distribution, stackability limits, mixed dimensions.
TypeScript Bin Packing Metaheuristics REST
07 / 08
Corporate Workshop  ·  1st Place
FiberCop Mapper
Won 1st place at the FiberCop corporate volunteering workshop at H-FARM College (Dec 2025). Built a software tool that maps community infrastructure problems and assigns priority scores for intervention scheduling.
Concept — Problem intake with severity classification, geographic clustering, and weighted priority scoring. Designed to help FiberCop field teams allocate resources to the highest-impact issues first. Presented and defended in a competitive team pitch format.
Priority Scoring Team Pitch H-FARM 1st Place
08 / 08
Commercial  ·  AI Automation
Carousel Generator
A personal Social Media Manager built for the talent manager of a 500K+ follower Instagram creator. User inputs a topic and the system produces a finished carousel — from raw idea to publish-ready slides in a single click.
Pipeline — Gemini generates slide text calibrated to the creator's empathic, professional tone. Next phase — automatic typesetting into pre-built brand templates with correct palette, fonts, and logo — returning ready-to-download images. Eliminates hours of manual Canva work per post.
React Gemini Brand Automation Commercial
04The PathContext
2021  ·  Peak
Competitive peak
Hearthstone Master Tour qualifier. Top rankings across TFT, Squad Busters, Mo.Co, and more. Built a Twitch presence as mrdarione. Learned what it means to perform when it actually matters.
2023  ·  Pivot
The pivot
Luxury retail at Karl Lagerfeld and Trussardi. Chemical Engineering at University of Padova. Searching for where strategy, technology, and building converge — then finding it in AI.
Now  ·  Build
Building & winning
H-FARM College, BSc AI & Data Science. Won 1st place at the FiberCop corporate workshop (Dec 2025). Shipping projects obsessively. Targeting elite international AI/DS roles.
05Play MeBullet Chess · 1 min
Interactive Demo

Play me in bullet chess — one minute, each side.

The opponent is an AI version of my own playing style: Italian Game as White, Caro-Kann as Black, sharp in the center, precise in tactics. It searches deep and doesn't give free material.

Each side gets 60 seconds total. No increment. Run out of time and you lose — same rule for the AI. Checkmate, stalemate, or flag.

Rule 01Standard chess rules — castling, en passant, promotion (to Queen) Rule 021:00 per side, depletes while it's your move Rule 03Click a piece, then click its destination Rule 04The AI plays strong — bring your best.
Opponent — Dario (AI)
1:00
Playing style: Italian / Caro-Kann
vs
You
1:00
Wins: 0
abcdefgh
87654321
Captured — by AI
Moves
Captured — by You
Status Press Start to begin. You play White.
06ArsenalTooling
Python PyTorch Stable-Baselines3 React React Native TypeScript Firebase Claude API OpenAI API Gemini KNIME Git Linux Probability & Statistics Game Theory Reinforcement Learning CUDA
07RésuméFormal Record
Education
BSc Artificial Intelligence & Data Science
Sep 2024 — Present
H-FARM College — University of Chichester · Venice, Italy
Core modules: Linear Algebra, Probability, Algorithms & Data Structures, Data Science. Active participant in extracurricular workshops and tech challenges.
Diploma — Automation & Robotics
2015 — 2020
ITIS Vito Volterra · San Donà di Piave (VE), Italy
Work Experience
Sales Assistant
Nov 2024 — Present
Karl Lagerfeld
Customer-facing sales in luxury fashion. Building client relationships, managing high-value transactions, consistent performance in a high-standard retail context.
Sales Assistant
May 2024 — Oct 2024
Trussardi
Sales and client engagement in premium fashion. Multi-lingual customer interactions in an international retail environment.
Sales Assistant
2023 — 2024
Karl Lagerfeld
First experience in luxury retail. Developed foundational client management and high-pressure communication skills.
Achievements
1st Place — FiberCop Corporate Workshop
Dec 2025
H-FARM College · Venice, Italy
Won a competitive corporate workshop organised by FiberCop. Developed and presented a software tool for mapping infrastructure issues and assigning intervention priorities.
Languages
ItalianNative
RomanianNative
EnglishB2
SpanishB1
FrenchA1
GermanA1
Certifications
Microsoft Power BIMicrosoft
Introduction to AICisco Networking
Python Essentials 1Cisco Networking
Claude API & Agent DevelopmentAnthropic · In Progress
Focus Areas
Reinforcement LearningPrimary
Probabilistic ModelingResearch
Multi-Agent SystemsExploring
Applied Game TheoryApplied
ARCAN
08 / Contact

Let's build something extraordinary.

Looking for internships, research collaborations, and ambitious projects in AI, data science, and intelligent systems. If you're building something hard, I want to hear about it.

LinkedIn GitHub · coming soon
Based In
Veneto, Italy
Availability
Q3 2026 · Internship / Research