| Name | scienceworld JSON |
| Version |
1.2.2
JSON |
| download |
| home_page | https://scienceworld.github.io |
| Summary | ScienceWorld: An interactive text environment to study AIagents on accomplishing tasks from the standardized elementary science curriculum. |
| upload_time | 2024-10-16 20:08:41 |
| maintainer | None |
| docs_url | None |
| author | Peter Jansen |
| requires_python | >=3.7 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<h1 align="center">
ScienceWorld
</h1>
<p align="center">
<!-- Version badge using shields.io -->
<a href="https://github.com/allenai/ScienceWorld/releases">
<img src="https://img.shields.io/github/v/release/allenai/ScienceWorld">
</a>
<!-- Link to tutorials badge using shields.io -->
<a href="https://huggingface.co/spaces/MarcCote/ScienceWorld">
<img src="https://img.shields.io/badge/🤗-Demo-yellow">
</a>
<!-- Follow on twitter badge using shields.io -->
<a href="https://sciworld.apps.allenai.org">
<img src="https://img.shields.io/badge/Website-green">
</a>
</p>
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum. This code accompanies the paper [ScienceWorld: Is your Textual Agent Smarter than a 5th grader?](https://arxiv.org/abs/2203.07540).
<h3 align="center"><img src="https://github.com/allenai/ScienceWorld/blob/main/media/scienceworld_environment.png" width="75%"/></h3>
### Demo and examples
You can try ScienceWorld yourself via our [HuggingFace Space](https://huggingface.co/spaces/MarcCote/ScienceWorld) or read some of the [playthrough transcripts](https://sciworld.apps.allenai.org/explore).
### Citation
```
@misc{scienceworld2022,
title={ScienceWorld: Is your Agent Smarter than a 5th Grader?},
author={Ruoyao Wang and Peter Jansen and Marc-Alexandre C{\^o}t{\'e} and Prithviraj Ammanabrolu},
year={2022},
eprint={2203.07540},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2203.07540}
}
```
# Quickstart
**Before running:** You will have to have `Java 1.8+` installed on your system (shipped with most linux distributions) and `Python 3.8+`. We recommend creating a conda environment like this:
```bash
conda create --name scienceworld python=3.8
conda activate scienceworld
```
Then, install ScienceWorld either from PyPi:
pip install scienceworld
or from source in development mode:
git clone https://github.com/allenai/ScienceWorld.git
cd ScienceWorld
pip install .
Run an example random agent, on task 13 (classification: place a non-living thing in a box), for 5 episodes:
python examples/random_agent.py --task-num=13 --num-episodes=5 --simplifications-preset easy
Run a user console where you can interact with the environment, on task 3 (change of state: melting):
python examples/human.py --task-num=3 --num-episodes=5
# Web Server Demo
A web server demo is also available, that allows running a ScienceWorld user console that can be interacted with in a web browser.
<h3 align="center"><img src="https://github.com/allenai/ScienceWorld/blob/main/media/web_demo_screenshot.png" width="75%"/></h3>
To run the web server demo:
```bash
conda create --name scienceworld python=3.8
conda activate scienceworld
pip install scienceworld[webserver]
```
Run the web server:
python examples/scienceworld-web-server-example.py
Point your web browser to:
`localhost:8080`
# ScienceWorld Design
ScienceWorld is written in Scala (2.12.9), and compiles using `sbt` into a JAR file that is run with Java. For convenience, a Python API is provided (Python >= 3.8), which interfaces using the `py4j` package.
If you modified the Scala code, you can recompile the JAR file by running:
```bash
./simulator/package.sh
pip install -e .
```
# Tasks
The tasks are listed in the table below along with their number of variations. Either the task ID or its name can be used to a task with `env.load()`.
| Task ID | Task Name | # Variations |
|-------|----------------------------------------------------|------|
| 1-1 | boil | 30 |
| 1-2 | melt | 30 |
| 1-3 | freeze | 30 |
| 1-4 | change-the-state-of-matter-of | 30 |
| 2-1 | use-thermometer | 540 |
| 2-2 | measure-melting-point-known-substance | 436 |
| 2-3 | measure-melting-point-unknown-substance | 300 |
| 3-1 | power-component | 20 |
| 3-2 | power-component-renewable-vs-nonrenewable-energy | 20 |
| 3-3 | test-conductivity | 900 |
| 3-4 | test-conductivity-of-unknown-substances | 600 |
| 4-1 | find-living-thing | 300 |
| 4-2 | find-non-living-thing | 300 |
| 4-3 | find-plant | 300 |
| 4-4 | find-animal | 300 |
| 5-1 | grow-plant | 126 |
| 5-2 | grow-fruit | 126 |
| 6-1 | chemistry-mix | 32 |
| 6-2 | chemistry-mix-paint-secondary-color | 36 |
| 6-3 | chemistry-mix-paint-tertiary-color | 36 |
| 7-1 | lifespan-longest-lived | 125 |
| 7-2 | lifespan-shortest-lived | 125 |
| 7-3 | lifespan-longest-lived-then-shortest-lived | 125 |
| 8-1 | identify-life-stages-1 | 14 |
| 8-2 | identify-life-stages-2 | 10 |
| 9-1 | inclined-plane-determine-angle | 168 |
| 9-2 | inclined-plane-friction-named-surfaces | 1386 |
| 9-3 | inclined-plane-friction-unnamed-surfaces | 162 |
| 10-1 | mendelian-genetics-known-plant | 120 |
| 10-2 | mendelian-genetics-unknown-plant | 480 |
# Baseline Agents
**DRRN:** https://github.com/cognitiveailab/drrn-scienceworld
**KG-A2C:** https://github.com/cognitiveailab/kga2c-scienceworld
**CALM:** https://github.com/cognitiveailab/calm-scienceworld
**Behavior Cloning and Decision Transformer:** https://github.com/cognitiveailab/t5-scienceworld
Raw data
{
"_id": null,
"home_page": "https://scienceworld.github.io",
"name": "scienceworld",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": null,
"author": "Peter Jansen",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/2d/98/101a8ee5fbbcadbdef6ae41b1254a1b17a6b54081e89b6ea88cf4a1523e3/scienceworld-1.2.2.tar.gz",
"platform": null,
"description": "<h1 align=\"center\">\nScienceWorld\n</h1>\n\n<p align=\"center\">\n<!-- Version badge using shields.io -->\n <a href=\"https://github.com/allenai/ScienceWorld/releases\">\n <img src=\"https://img.shields.io/github/v/release/allenai/ScienceWorld\">\n </a>\n<!-- Link to tutorials badge using shields.io -->\n <a href=\"https://huggingface.co/spaces/MarcCote/ScienceWorld\">\n <img src=\"https://img.shields.io/badge/\ud83e\udd17-Demo-yellow\">\n </a>\n<!-- Follow on twitter badge using shields.io -->\n <a href=\"https://sciworld.apps.allenai.org\">\n <img src=\"https://img.shields.io/badge/Website-green\">\n </a>\n</p>\n\nScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum. This code accompanies the paper [ScienceWorld: Is your Textual Agent Smarter than a 5th grader?](https://arxiv.org/abs/2203.07540).\n\n<h3 align=\"center\"><img src=\"https://github.com/allenai/ScienceWorld/blob/main/media/scienceworld_environment.png\" width=\"75%\"/></h3>\n\n### Demo and examples\n\nYou can try ScienceWorld yourself via our [HuggingFace Space](https://huggingface.co/spaces/MarcCote/ScienceWorld) or read some of the [playthrough transcripts](https://sciworld.apps.allenai.org/explore).\n\n### Citation\n```\n@misc{scienceworld2022,\n title={ScienceWorld: Is your Agent Smarter than a 5th Grader?},\n author={Ruoyao Wang and Peter Jansen and Marc-Alexandre C{\\^o}t{\\'e} and Prithviraj Ammanabrolu},\n year={2022},\n eprint={2203.07540},\n archivePrefix={arXiv},\n primaryClass={cs.CL},\n url={https://arxiv.org/abs/2203.07540}\n}\n```\n\n# Quickstart\n**Before running:** You will have to have `Java 1.8+` installed on your system (shipped with most linux distributions) and `Python 3.8+`. We recommend creating a conda environment like this:\n\n```bash\nconda create --name scienceworld python=3.8\nconda activate scienceworld\n```\n\nThen, install ScienceWorld either from PyPi:\n\n pip install scienceworld\n\nor from source in development mode:\n\n git clone https://github.com/allenai/ScienceWorld.git\n cd ScienceWorld\n pip install .\n\n\nRun an example random agent, on task 13 (classification: place a non-living thing in a box), for 5 episodes:\n\n python examples/random_agent.py --task-num=13 --num-episodes=5 --simplifications-preset easy\n\nRun a user console where you can interact with the environment, on task 3 (change of state: melting):\n\n python examples/human.py --task-num=3 --num-episodes=5\n\n\n# Web Server Demo\n\nA web server demo is also available, that allows running a ScienceWorld user console that can be interacted with in a web browser.\n\n<h3 align=\"center\"><img src=\"https://github.com/allenai/ScienceWorld/blob/main/media/web_demo_screenshot.png\" width=\"75%\"/></h3>\n\nTo run the web server demo:\n```bash\nconda create --name scienceworld python=3.8\nconda activate scienceworld\npip install scienceworld[webserver]\n```\n\nRun the web server:\n\n python examples/scienceworld-web-server-example.py\n\nPoint your web browser to:\n`localhost:8080`\n\n\n# ScienceWorld Design\nScienceWorld is written in Scala (2.12.9), and compiles using `sbt` into a JAR file that is run with Java. For convenience, a Python API is provided (Python >= 3.8), which interfaces using the `py4j` package.\n\nIf you modified the Scala code, you can recompile the JAR file by running:\n```bash\n./simulator/package.sh\npip install -e .\n```\n\n# Tasks\nThe tasks are listed in the table below along with their number of variations. Either the task ID or its name can be used to a task with `env.load()`.\n\n| Task ID | Task Name | # Variations |\n|-------|----------------------------------------------------|------|\n| 1-1 | boil | 30 |\n| 1-2 | melt | 30 |\n| 1-3 | freeze | 30 |\n| 1-4 | change-the-state-of-matter-of | 30 |\n| 2-1 | use-thermometer | 540 |\n| 2-2 | measure-melting-point-known-substance | 436 |\n| 2-3 | measure-melting-point-unknown-substance | 300 |\n| 3-1 | power-component | 20 |\n| 3-2 | power-component-renewable-vs-nonrenewable-energy | 20 |\n| 3-3 | test-conductivity | 900 |\n| 3-4 | test-conductivity-of-unknown-substances | 600 |\n| 4-1 | find-living-thing | 300 |\n| 4-2 | find-non-living-thing | 300 |\n| 4-3 | find-plant | 300 |\n| 4-4 | find-animal | 300 |\n| 5-1 | grow-plant | 126 |\n| 5-2 | grow-fruit | 126 |\n| 6-1 | chemistry-mix | 32 |\n| 6-2 | chemistry-mix-paint-secondary-color | 36 |\n| 6-3 | chemistry-mix-paint-tertiary-color | 36 |\n| 7-1 | lifespan-longest-lived | 125 |\n| 7-2 | lifespan-shortest-lived | 125 |\n| 7-3 | lifespan-longest-lived-then-shortest-lived | 125 |\n| 8-1 | identify-life-stages-1 | 14 |\n| 8-2 | identify-life-stages-2 | 10 |\n| 9-1 | inclined-plane-determine-angle | 168 |\n| 9-2 | inclined-plane-friction-named-surfaces | 1386 |\n| 9-3 | inclined-plane-friction-unnamed-surfaces | 162 |\n| 10-1 | mendelian-genetics-known-plant | 120 |\n| 10-2 | mendelian-genetics-unknown-plant | 480 |\n\n# Baseline Agents\n**DRRN:** https://github.com/cognitiveailab/drrn-scienceworld\n\n**KG-A2C:** https://github.com/cognitiveailab/kga2c-scienceworld\n\n**CALM:** https://github.com/cognitiveailab/calm-scienceworld\n\n**Behavior Cloning and Decision Transformer:** https://github.com/cognitiveailab/t5-scienceworld\n",
"bugtrack_url": null,
"license": null,
"summary": "ScienceWorld: An interactive text environment to study AIagents on accomplishing tasks from the standardized elementary science curriculum.",
"version": "1.2.2",
"project_urls": {
"Homepage": "https://scienceworld.github.io"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9f7d3274b58a3267a4004edd7e72cb820f0609e47447e2f8eae9a2a0c776668b",
"md5": "4d9996741915a525a79f21b252f21f2f",
"sha256": "afef9af68e14d1bd512ffaf01bb356f876afe1b0cc31107cf5e3317d363dba3a"
},
"downloads": -1,
"filename": "scienceworld-1.2.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "4d9996741915a525a79f21b252f21f2f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 7283832,
"upload_time": "2024-10-16T20:08:38",
"upload_time_iso_8601": "2024-10-16T20:08:38.372642Z",
"url": "https://files.pythonhosted.org/packages/9f/7d/3274b58a3267a4004edd7e72cb820f0609e47447e2f8eae9a2a0c776668b/scienceworld-1.2.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2d98101a8ee5fbbcadbdef6ae41b1254a1b17a6b54081e89b6ea88cf4a1523e3",
"md5": "40f0f7451c87c5bdb6450e77c34673f8",
"sha256": "a3fced7240b09c9727b9ef2b9fee7377a1235886d85d40f2ceb6098be436338d"
},
"downloads": -1,
"filename": "scienceworld-1.2.2.tar.gz",
"has_sig": false,
"md5_digest": "40f0f7451c87c5bdb6450e77c34673f8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 7286075,
"upload_time": "2024-10-16T20:08:41",
"upload_time_iso_8601": "2024-10-16T20:08:41.630507Z",
"url": "https://files.pythonhosted.org/packages/2d/98/101a8ee5fbbcadbdef6ae41b1254a1b17a6b54081e89b6ea88cf4a1523e3/scienceworld-1.2.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-16 20:08:41",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "scienceworld"
}
