HuggingEnvs/data-agent-training-comparison-trackio
15.9 MB
AI & ML interests
RL Environments at Scale
Recent Activity
View all activity
Organization Card
🤗 HuggingEnvs: Open RL Environments
HuggingEnvs is a home for end-to-end RL environment recipes, built to make it easier to explore, reproduce, train, and evaluate agent systems.
Explore complete and reproducible environment projects from us and the community, including:
- 🌍 Open RL environments
- 🧩 End-to-end environment recipes
- 💻 Complete implementations
- 📦 Models, datasets, and artifacts
- 🧪 Training and evaluation setups
- 🚀 Demos and Spaces
- 📚 Tutorials and guides
All the reproducible code — environments, rollouts, training configs, notebooks, article and slide sources — lives in one repo: github.com/adithya-s-k/HuggingEnvs. The artifacts those produce live here on the Hub.
HuggingEnvs Projects
A growing collection of open projects, environments, resources, and artifacts.
| Project | What it is | Explore |
|---|---|---|
| HuggingEnvs Academy | Articles, guides, tutorials, slides, and hands-on resources for learning how to build RL environments and agent systems. | Explore → |
| Data Agent | Training SLMs for data science with multi-harness RL environments. | Explore → |
Each numbered project below is a self-contained recipe: an environment, a training run, and every artifact it produced.
| # | Project | What it is | Explore |
|---|---|---|---|
| 00 | RL Environments 101 | Three environments implemented six times over, one per framework. Same logic, six dialects. | Source → |
| 01 | LaTeX OCR | Qwen3-VL-2B trained to read rendered math into LaTeX, scored by a reward served from a live Space. | Space → |
| 02 | Watercolour | Qwen3.5-35B-A3B trained to paint watercolours by writing p5.brush sketches, rewarded by taste rather than correctness. | Collection → |
| 03 | GeoGuesser | A multi-turn visual geolocation environment, and the 4B trained on it until it outscored gpt-5.4-mini and claude-haiku-4.5. |
Collection → |
Articles & Talks
| What it covers | Read / Watch | |
|---|---|---|
| 📖 The Ultimate Guide to RL Environments | Building and scaling RL environments in the LLM era — how frameworks are built, how rewards are wired, how they scale to thousands of concurrent sessions. | Read → |
| 🎞️ RL Environments 101 | From "what is an env?" to training your own: RL fundamentals → environment anatomy → OpenEnv → training with TRL. | Watch → |
| 📈 Scaling RL for LLMs | RL environments and RL training — what an environment is, how reward hacking happens, how to train against your own. AMD AI Dev Day. | Watch → |
| 🔀 Multi-Harness Training | OpenEnv × Harbor — why an environment's failure model decides whether it can be trained against. | Watch → |
| 🌍 How to turn a game into an RL environment | The technical intuition, end to end: curating the data, designing the environment, shipping it with OpenEnv, and training a 4B against it with TRL. | Read → |
Environments
Three reference environments, each implemented across six frameworks — openenv, ors, nemo_gym, verifiers, skyrl_gym, gem. Same logic, six dialects. Source →
| Environment | Tools | OpenEnv | ORS | NeMo Gym |
|---|---|---|---|---|
| Jupyter agent — real code execution in an E2B sandbox | 4 | Space | Space | Space |
| Wordle — multi-turn, pure Python, no backend | 1 | Space | Space | Space |
| Desktop — computer-use, vision-driven Linux desktop | 19 | Space | Space | — |
Build your own
Five agent skills turn a plain-English description into a runnable RL environment across four frameworks — works with Claude Code, Cursor, Codex, OpenCode, Gemini CLI and others.
npx skills add adithya-s-k/HuggingEnvs
We're looking for new end-to-end recipes — a task, an environment, a training run, and honest results. Contributing guide →
spaces 20
Running
The ultimate guide to multi-harness RL
🔀
Training and evals together across many agent harnesses
Running
Agents
Data Agent Training Comparison
📈
Visualize training and evaluation metrics for your project
Sleeping
Data Agent Blackbox OpenCode Env
🚀
Run OpenCode data analysis tasks in a sandbox
Sleeping
Data Agent Blackbox Harbor Env
🚀
Run a coding agent on a chosen data task via your model endpoint
Sleeping
Nayana Multilingual OCR
📖
Score multilingual OCR and document QA answers
Sleeping
Data Agent SETA Whitebox Env
🚀
Explore data tasks, run commands, and submit answers
models 6
HuggingEnvs/qwen3.5-latex-ocr-grpo
Image-Text-to-Text • 5B • Updated • 17
HuggingEnvs/geoguesser-qwen3.5-4b-grpo-v3
Image-Text-to-Text • Updated • 68
HuggingEnvs/geoguesser-qwen3.5-4b-grpo
Image-Text-to-Text • Updated • 38
HuggingEnvs/watercolour-grpo-hps-led
Reinforcement Learning • Updated • 25 • 1
HuggingEnvs/watercolour-grpo-judge-led
Reinforcement Learning • Updated • 28 • 1
HuggingEnvs/watercolour-grpo-hps-only
Reinforcement Learning • Updated • 39 • 1
datasets 27
HuggingEnvs/data-agent-experiment-results
Updated • 114
HuggingEnvs/data-agent-daytona-repro
Viewer • Updated • 1 • 95
HuggingEnvs/repo2rlenv-terminalworld
Updated • 109
HuggingEnvs/repo2rlenv-seta-seed2synth
Updated • 88
HuggingEnvs/repo2rlenv-swe-next
Updated • 129
HuggingEnvs/repo2rlenv-swe-smith
Updated • 137
HuggingEnvs/repo2rlenv-swe-gen
Updated • 125
HuggingEnvs/repo2rlenv-swe-flow
Updated • 7.02k
HuggingEnvs/repo2rlenv-r2e
Updated • 130
HuggingEnvs/repo2rlenv-r2e-gym
Updated • 138