diff --git a/README.md b/README.md index 5717b0e2f..3cdfe5241 100644 --- a/README.md +++ b/README.md @@ -1,14 +1,13 @@ # ManiSkill2 -![teaser](figures/teaser.jpg) +![teaser](figures/teaser_v2.jpg) [![PyPI version](https://badge.fury.io/py/mani-skill2.svg)](https://badge.fury.io/py/mani-skill2) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/haosulab/ManiSkill2/blob/main/examples/tutorials/1_quickstart.ipynb) [![Docs status](https://img.shields.io/badge/docs-passing-brightgreen.svg)](https://haosulab.github.io/ManiSkill2) -ManiSkill2 is a unified benchmark for learning generalizable robotic manipulation skills powered by [SAPIEN](https://sapien.ucsd.edu/). **It features 20 out-of-box task families with 2000+ diverse object models and 4M+ demonstration frames**. Moreover, it empowers fast visual input learning algorithms -so that **a CNN-based policy can collect samples at about 2000 FPS with 1 GPU and 16 processes on a workstation**. The benchmark can be used to study a wide range of algorithms: 2D & 3D vision-based reinforcement learning, imitation learning, sense-plan-act, etc. +ManiSkill2 is a unified benchmark for learning generalizable robotic manipulation skills powered by [SAPIEN](https://sapien.ucsd.edu/). **It features 20 out-of-box task families with 2000+ diverse object models and 4M+ demonstration frames**. Moreover, it empowers fast visual input learning algorithms so that **a CNN-based policy can collect samples at about 2000 FPS with 1 GPU and 16 processes on a workstation**. The benchmark can be used to study a wide range of algorithms: 2D & 3D vision-based reinforcement learning, imitation learning, sense-plan-act, etc. Please refer our [documentation](https://haosulab.github.io/ManiSkill2) to learn more information. diff --git a/figures/teaser.jpg b/figures/teaser_v2.jpg similarity index 100% rename from figures/teaser.jpg rename to figures/teaser_v2.jpg diff --git a/requirements.txt b/requirements.txt index b9e925779..6dc6a87c8 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,7 +2,7 @@ numpy<1.24 scipy gym>=0.18.3,<=0.21.0 -sapien>=2.2.1 +sapien==2.2.1 # basic h5py pyyaml diff --git a/setup.py b/setup.py index 6719ec18d..e4a319cb3 100644 --- a/setup.py +++ b/setup.py @@ -1,6 +1,8 @@ from setuptools import find_packages, setup -long_description = """ManiSkill2 is a large-scale robotic manipulation benchmark, focusing on learning generalizable robot agents and manipulation skills. It features 2000+ diverse objects, 20 task categories, and a large-scale demonstration set in [SAPIEN](https://sapien.ucsd.edu/), a fully-physical, realistic simulator. The benchmark can be used to study 2D & 3D vision-based imitation learning, reinforcement learning, and motion planning, etc.""" +long_description = """ManiSkill2 is a unified benchmark for learning generalizable robotic manipulation skills powered by [SAPIEN](https://sapien.ucsd.edu/). **It features 20 out-of-box task families with 2000+ diverse object models and 4M+ demonstration frames**. Moreover, it empowers fast visual input learning algorithms so that **a CNN-based policy can collect samples at about 2000 FPS with 1 GPU and 16 processes on a workstation**. The benchmark can be used to study a wide range of algorithms: 2D & 3D vision-based reinforcement learning, imitation learning, sense-plan-act, etc. + +Please refer our [documentation](https://haosulab.github.io/ManiSkill2) to learn more information.""" def read_requirements(): @@ -12,7 +14,7 @@ def read_requirements(): setup( name="mani_skill2", - version="0.3.3", + version="0.4.0", description="ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills", long_description=long_description, long_description_content_type="text/markdown",