Welcome Sameer S Katte! sameerkatte@gmail.com Copy Join the Discord Community All announcements, mentor access, and team matching happens here. Join Discord QUICK TOGGLe Team form Submission Preparatory Course Start Assessment FAQs step 1 How will you compete? Choose solo or team before you can start the assessment Step 1 Complete You’ve joined The Cook House. The team has been finalized for you. πŸ‘€ Sai Jadhav skvj369@gmail.com Team Lead πŸ‘€ Sameer S Katte sameerkatte@gmail.com You πŸ”’ Team is finalized. You’re all set β€” no further action needed. PROBLEM STATEMENT Round 1 β€” Problem Statement The Task Build a complete, real-world OpenEnv environment that an AI agent can learn from through the standard step() / reset() / state() API. Key Requirements at a Glance Must simulate a real-world task (not games or toys) Implement full OpenEnv spec: typed models, step()/reset()/state(), openenv.yaml Minimum 3 tasks with agent graders (easy β†’ medium β†’ hard, scores 0.0–1.0) Meaningful reward function with partial progress signals Baseline inference script with reproducible scores Deploy to Hugging Face Spaces + working Dockerfile README with environment description, action/observation spaces, setup instructions Functional Requirements Real-world task simulation The environment must simulate a task humans actually do. Not games, not toys. Examples: email triage, code review, data cleaning, scheduling, customer support, content moderation. OpenEnv spec compliance Implement the full OpenEnv interface: typed Observation, Action, and Reward Pydantic models. step(action) β†’ returns observation, reward, done, info. reset() β†’ returns initial observation. state() β†’ returns current state. openenv.yaml with metadata. Tested via openenv validate. Minimum 3 tasks with agent graders Each task defines a concrete objective an agent must accomplish, with a programmatic grader that scores performance (0.0–1.0). Tasks should range: easy β†’ medium β†’ hard. Graders must have clear, deterministic success/failure criteria. Meaningful reward function Provides signal over the full trajectory (not just binary end-of-episode). Rewards partial progress toward task completion. Penalizes clearly undesirable behavior (e.g. infinite loops, destructive actions). Baseline inference script Uses the OpenAI API client to run a model against the environment. Reads API credentials from environment variables (OPENAI_API_KEY). Produces a reproducible baseline score on all 3 tasks. Detailed Requirements Non-Functional Requirements Deploys to a Hugging Face Space Environment must run as a containerized HF Space tagged with openenv. Containerized execution Must include a working Dockerfile. The environment should start cleanly with docker build + docker run. Documentation README must include: environment description and motivation, action and observation space definitions, task descriptions with expected difficulty, setup and usage instructions, baseline scores. Parameter Weight Description Real-world utility 30% Does the environment model a genuine task? Would someone actually use this to train or evaluate agents? Task & grader quality 25% Are tasks well-defined with clear objectives? Do graders accurately and fairly measure success? Meaningful difficulty progression? Environment design 20% Clean state management, sensible action/observation spaces, good reward shaping, proper episode boundaries. Code quality & spec compliance 15% Follows OpenEnv spec, clean project structure, typed models, documented, tested, Dockerfile works. Creativity & novelty 10% Novel problem domain, interesting mechanics, clever reward design, original approach. Scoring Breakdown Real-world utility (30%) β€’ 0–5: Toy/artificial problem with no practical application β€’ 6–15: Valid domain but shallow modeling of the real task β€’ 16–25: Good domain modeling, would be useful for agent evaluation β€’ 26–30: Excellent β€” fills a real gap, immediate value for the RL/agent community Task & grader quality (25%) β€’ 3+ tasks with difficulty range? β€’ Graders produce scores between 0.0–1.0? β€’ Graders deterministic and reproducible? β€’ Hard task genuinely challenges frontier models? Environment design (20%) β€’ reset() produces clean state? β€’ Action/observation types well-designed and documented? β€’ Reward function provides useful varying signal (not just sparse)? β€’ Episode boundaries sensible? Code quality & spec compliance (15%) β€’ openenv validate passes? β€’ docker build && docker run works? β€’ HF Space deploys and responds? β€’ Baseline script runs and reproduces scores? Creativity & novelty (10%) β€’ Domain we haven’t seen in OpenEnv before? β€’ Reward design has interesting properties? β€’ Clever mechanics that make the environment engaging? Evaluation Criteria Phase 1: Automated Validation Pass/fail gate β€” HF Space deploys, OpenEnv spec compliance, Dockerfile builds, baseline reproduces, 3+ tasks with graders. Phase 2: Agentic Evaluation Scored β€” baseline agent re-run, standard Open LLM agent (e.g. Nemotron 3 Super) run against all environments, score variance check. Phase 3: Human Review Top submissions reviewed by Meta and Hugging Face engineers for real-world utility, creativity, and exploit checks. Disqualification Criteria Environment does not deploy or respond Plagiarized or trivially modified existing environments Graders that always return the same score No baseline inference script How Judging works Pre-Submission Checklist β€” all must pass or you're disqualified HF Space deploys Automated ping to the Space URL β€” must return 200 and respond to reset() OpenEnv spec compliance Validate openenv.yaml, typed models, step()/reset()/state() endpoints Dockerfile builds Automated docker build on the submitted repo Baseline reproduces Run the submitted inference script β€” must complete without error and produce scores 3+ tasks with graders Enumerate tasks, run each grader, verify scores in 0.0–1.0 range Additional Instructions Before submitting, ensure the following variables are defined in your environment configuration: API_BASE_URL The API endpoint for the LLM. MODEL_NAME The model identifier to use for inference. HF_TOKEN Your Hugging Face / API key. The inference script must be named `inference.py` and placed in the root directory of the project Participants must use OpenAI Client for all LLM calls using above variables Infra Restrictions Runtime of inference script should be less than 20min Make sure your env and inference can run on a machine with vcpu=2, memory=8gb Validator Run the pre-submission validation script before submitting Sample Inference Script """ Inference Script Example =================================== MANDATORY - Before submitting, ensure the following variables are defined in your environment configuration: API_BASE_URL The API endpoint for the LLM. MODEL_NAME The model identifier to use for inference. HF_TOKEN Your Hugging Face / API key. - The inference script must be named `inference.py` and placed in the root directory of the project - Participants must use OpenAI Client for all LLM calls using above variables """ import os import re import base64 import textwrap from io import BytesIO from typing import List, Optional, Dict from openai import OpenAI import numpy as np from PIL import Image from browsergym_env import BrowserGymAction, BrowserGymEnv API_BASE_URL = os.getenv("API_BASE_URL") // "https://router.huggingface.co/v1" API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY") MODEL_NAME = os.getenv("MODEL_NAME") MAX_STEPS = 8 MAX_DOM_CHARS = 3500 TEMPERATURE = 0.2 MAX_TOKENS = 200 FALLBACK_ACTION = "noop()" DEBUG = True ACTION_PREFIX_RE = re.compile( r"^(action|next action)\s*[:\-]\s*", re.IGNORECASE, ) ACTION_PATTERN = re.compile(r"[A-Za-z_]+\s*\(.*\)", re.DOTALL) SYSTEM_PROMPT = textwrap.dedent( """ You control a web browser through BrowserGym. Reply with exactly one action string. The action must be a valid BrowserGym command such as: - noop() - click('') - type('selector', 'text to enter') - fill('selector', 'text to enter') - send_keys('Enter') - scroll('down') Use single quotes around string arguments. When clicking, use the BrowserGym element IDs (BIDs) listed in the user message. If you are unsure, respond with noop(). Do not include explanations or additional text. """ ).strip() Pre Validation Script #!/usr/bin/env bash # # validate-submission.sh β€” OpenEnv Submission Validator # # Checks that your HF Space is live, Docker image builds, and openenv validate passes. # # Prerequisites: # - Docker: https://docs.docker.com/get-docker/ # - openenv-core: pip install openenv-core # - curl (usually pre-installed) # # Run: # curl -fsSL https://raw.githubusercontent.com///main/scripts/validate-submission.sh | bash -s -- [repo_dir] # # Or download and run locally: # chmod +x validate-submission.sh # ./validate-submission.sh [repo_dir] # # Arguments: # ping_url Your HuggingFace Space URL (e.g. https://your-space.hf.space) # repo_dir Path to your repo (default: current directory) # # Examples: # ./validate-submission.sh https://my-team.hf.space # ./validate-submission.sh https://my-team.hf.space ./my-repo # set -uo pipefail DOCKER_BUILD_TIMEOUT=600 if [ -t 1 ]; then RED='\033[0;31m' GREEN='\033[0;32m' YELLOW='\033[1;33m' BOLD='\033[1m' NC='\033[0m' else RED='' GREEN='' YELLOW='' BOLD='' NC='' fi run_with_timeout() { local secs="$1"; shift if command -v timeout &>/dev/null; then timeout "$secs" "$@" elif command -v gtimeout &>/dev/null; then gtimeout "$secs" "$@" else "$@" & local pid=$! ( sleep "$secs" && kill "$pid" 2>/dev/null ) & local watcher=$! wait "$pid" 2>/dev/null local rc=$? kill "$watcher" 2>/dev/null wait "$watcher" 2>/dev/null return $rc fi } portable_mktemp() { local prefix="${1:-validate}" Submission window opens on 28th March Submit your Assessment β†’ Study material Preparatory Course 4 modules Β· ~3.5 hours Each module: read the README first, then open the notebook in Colab. No local setup needed. Module 1: Why OpenEnv? ESSENTIAL FOR ROUND 1 45 min Module 2: Using Existing Environments ESSENTIAL FOR ROUND 1 50 min Module 3: Deploying Environments ESSENTIAL FOR ROUND 1 45 min Module 4: Building Your Own Environment MOST IMPORTANT FOR ROUND 1 60 min View full course repository GUIDE Round 1 Guide What to Expect Prerequisites How to Submit When Round 1 opens, you'll choose 1 of 4–5 problem statements and build an OpenEnv environment around it. Example of what a problem statement looks like "Build a mini-game RL environment with clearly defined tasks, automated graders, and reward logic using the OpenEnv framework." β†’ Create a mini-game an AI agent can play β†’ Define tasks with increasing difficulty β†’ Write graders that verify task completion β†’ Define reward logic for scoring β†’ Package using OpenEnv for automated evaluation Evaluation Criteria Runtime correctness Runs without errors Interface compliance Follows OpenEnv standard Task design Clear, realistic, testable Grading logic Reward system makes sense