skip to content
← all projects

Winter 2026

Reinforcement learning team

The beginner Winter Projects track, training agents from scratch to learn what the abstraction is actually doing underneath.

RLbeginner

The beginner track of Winter Projects 2026. Where the summer teams built on top of large models, this team goes the other way — training agents from scratch to see what's actually happening underneath the abstraction.

Reinforcement learning is a deliberate choice for a beginner track. It's visual, the feedback loop is immediate, and you cannot fake understanding of it: either the agent learns or it doesn't.

What the team had to work out

  • Starting from no assumed background in ML
  • Reward shaping, which is where most first RL projects stall

Other builds

Winter 2026

SIGIL

A shared store where AI agents claim work by tagging it, instead of talking to each other — built to measure whether that actually helps.

Summer 2025/26

Knowledge agent

A retrieval-augmented agent that answers questions over the club's own document corpus instead of guessing.

Summer 2025/26

Marketing agent

Drafts and schedules campaign content in the club's voice, so the marketing team edits instead of starting from blank.

Build the next one

Applications for each projects intake go out to members first. No experience assumed — there's a beginner track for exactly that reason.

Join the clubSponsor a project →