Spaces:
Running
Running
Update links for the HuggingEnvs repo rename; add articles, talks and environments
Browse files
README.md
CHANGED
|
@@ -11,8 +11,8 @@ license: mit
|
|
| 11 |
|
| 12 |

|
| 13 |
|
| 14 |
-
[](https://huggingface.co/spaces/AdithyaSK/rl-environments-101-slides)
|
| 17 |
|
| 18 |
# π€ HuggingEnvs: Open RL Environments
|
|
@@ -29,6 +29,8 @@ Explore complete and reproducible environment projects from us and the community
|
|
| 29 |
* π **Demos and Spaces**
|
| 30 |
* π **Tutorials and guides**
|
| 31 |
|
|
|
|
|
|
|
| 32 |
|
| 33 |
# HuggingEnvs Projects
|
| 34 |
A growing collection of open projects, environments, resources, and artifacts.
|
|
@@ -38,3 +40,34 @@ A growing collection of open projects, environments, resources, and artifacts.
|
|
| 38 |
| **HuggingEnvs Academy** | Articles, guides, tutorials, slides, and hands-on resources for learning how to build RL environments and agent systems. | [Explore β](https://huggingface.co/collections/HuggingEnvs/huggingenvs-academy) |
|
| 39 |
| **Data Agent** | Training SLMs for data science with multi-harness RL environments. | [Explore β](https://huggingface.co/collections/HuggingEnvs/data-agent) |
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |

|
| 13 |
|
| 14 |
+
[](https://github.com/adithya-s-k/HuggingEnvs)
|
| 15 |
+
[](https://huggingface.co/spaces/AdithyaSK/rl-environments-guide)
|
| 16 |
[](https://huggingface.co/spaces/AdithyaSK/rl-environments-101-slides)
|
| 17 |
|
| 18 |
# π€ HuggingEnvs: Open RL Environments
|
|
|
|
| 29 |
* π **Demos and Spaces**
|
| 30 |
* π **Tutorials and guides**
|
| 31 |
|
| 32 |
+
All the reproducible code β environments, rollouts, training configs, notebooks, article and slide sources β lives in one repo: **[github.com/adithya-s-k/HuggingEnvs](https://github.com/adithya-s-k/HuggingEnvs)**. The artifacts those produce live here on the Hub.
|
| 33 |
+
|
| 34 |
|
| 35 |
# HuggingEnvs Projects
|
| 36 |
A growing collection of open projects, environments, resources, and artifacts.
|
|
|
|
| 40 |
| **HuggingEnvs Academy** | Articles, guides, tutorials, slides, and hands-on resources for learning how to build RL environments and agent systems. | [Explore β](https://huggingface.co/collections/HuggingEnvs/huggingenvs-academy) |
|
| 41 |
| **Data Agent** | Training SLMs for data science with multi-harness RL environments. | [Explore β](https://huggingface.co/collections/HuggingEnvs/data-agent) |
|
| 42 |
|
| 43 |
+
|
| 44 |
+
# Articles & Talks
|
| 45 |
+
|
| 46 |
+
| | What it covers | Read / Watch |
|
| 47 |
+
| :--- | :--- | :--- |
|
| 48 |
+
| π **The Ultimate Guide to RL Environments** | Building and scaling RL environments in the LLM era β how frameworks are built, how rewards are wired, how they scale to thousands of concurrent sessions. | [Read β](https://huggingface.co/spaces/AdithyaSK/rl-environments-guide) |
|
| 49 |
+
| ποΈ **RL Environments 101** | From "what is an env?" to training your own: RL fundamentals β environment anatomy β OpenEnv β training with TRL. | [Watch β](https://huggingface.co/spaces/AdithyaSK/rl-environments-101-slides) |
|
| 50 |
+
| π **Scaling RL for LLMs** | RL environments and RL training β what an environment is, how reward hacking happens, how to train against your own. AMD AI Dev Day. | [Watch β](https://huggingface.co/spaces/AdithyaSK/scaling-rl-for-llms-amd-ai-dev-day) |
|
| 51 |
+
| π **Multi-Harness Training** | OpenEnv Γ Harbor β why an environment's failure model decides whether it can be trained against. | [Watch β](https://huggingface.co/spaces/AdithyaSK/multi-harness-training-slides) |
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
# Environments
|
| 55 |
+
|
| 56 |
+
Three reference environments, each implemented across six frameworks β `openenv`, `ors`, `nemo_gym`, `verifiers`, `skyrl_gym`, `gem`. Same logic, six dialects. [Source β](https://github.com/adithya-s-k/HuggingEnvs/tree/main/00-environments-101)
|
| 57 |
+
|
| 58 |
+
| Environment | Tools | OpenEnv | ORS | NeMo Gym |
|
| 59 |
+
| :--- | :--: | :--- | :--- | :--- |
|
| 60 |
+
| **Jupyter agent** β real code execution in an E2B sandbox | 4 | [Space](https://huggingface.co/spaces/AdithyaSK/jupyter-agent-openenv) | [Space](https://huggingface.co/spaces/AdithyaSK/jupyter-agent-ors) | [Space](https://huggingface.co/spaces/AdithyaSK/jupyter-agent-nemo-gym) |
|
| 61 |
+
| **Wordle** β multi-turn, pure Python, no backend | 1 | [Space](https://huggingface.co/spaces/AdithyaSK/wordle-openenv) | [Space](https://huggingface.co/spaces/AdithyaSK/wordle-ors) | [Space](https://huggingface.co/spaces/AdithyaSK/wordle-nemo-gym) |
|
| 62 |
+
| **Desktop** β computer-use, vision-driven Linux desktop | 19 | [Space](https://huggingface.co/spaces/AdithyaSK/desktop-openenv) | [Space](https://huggingface.co/spaces/AdithyaSK/desktop-ors) | β |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
# Build your own
|
| 66 |
+
|
| 67 |
+
Five agent skills turn a plain-English description into a runnable RL environment across four frameworks β works with Claude Code, Cursor, Codex, OpenCode, Gemini CLI and others.
|
| 68 |
+
|
| 69 |
+
```bash
|
| 70 |
+
npx skills add adithya-s-k/HuggingEnvs
|
| 71 |
+
```
|
| 72 |
+
|
| 73 |
+
**We're looking for new end-to-end recipes** β a task, an environment, a training run, and honest results. [Contributing guide β](https://github.com/adithya-s-k/HuggingEnvs/blob/main/CONTRIBUTING.md)
|