Skip to content
View AdarshGoel2001's full-sized avatar
2 followers · 0 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Pull Shark

Block or report AdarshGoel2001

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AdarshGoel2001/README.md

Hi, I'm Adarsh

ML & robotics engineer based in Bengaluru.

Currently shipping open-source research-engineering on AutomationBench — a four-layer retrieval pipeline that lifts strict pass-rate ~3× over the paper's BM25 baseline. Reproducing DreamerV3 and DIAMOND in rl-lab.

Previously, I was the technical program owner on a robotics dark-store pilot and ran multi-program oversight on the Gen 3 scooter portfolio at Ola Electric's Founder's Office, reporting directly to the CEO. Co-founded Glitch House (offline robotics and AI for middle-schoolers) until April 2026.

Self-taught path: JEE → BITS Pilani → Ola → ML.

📄 resume → adarshgoel2001.github.io ✉️ adarshgoel@gmail.com

Pinned Loading

  1. AutomationBench AutomationBench Public

    Forked from zapier/AutomationBench

    Better retrieval for Zapier's agent-workflow benchmark — 3× strict-pass lift over BM25 baseline. WIP writeup.

    Python 1

  2. orbitWars orbitWars Public

    RL self-play agent for a 1-second-per-turn CPU-budget Kaggle game. 100× inference speedup via radar + dynamic tokens + axial attention.

    Jupyter Notebook 1

  3. rl-lab rl-lab Public

    Modular world-models framework (PyTorch). Interchangeable vision, dynamics, and controller modules. In-progress reproductions of DreamerV3, DIAMOND, and a PROWL-style continual-learning prioritized…

    Python 1

  4. adarshgoel2001.github.io adarshgoel2001.github.io Public

    My resume

    HTML