https://github.com/servicenow/minitouch
MiniTouch is a ServiceNow Research project that was started at Element AI.
https://github.com/servicenow/minitouch
Last synced: 5 months ago
JSON representation
MiniTouch is a ServiceNow Research project that was started at Element AI.
- Host: GitHub
- URL: https://github.com/servicenow/minitouch
- Owner: ServiceNow
- License: apache-2.0
- Created: 2021-02-26T21:02:43.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2023-07-05T19:28:33.000Z (over 2 years ago)
- Last Synced: 2024-03-30T05:22:36.937Z (almost 2 years ago)
- Language: Python
- Homepage:
- Size: 12.8 MB
- Stars: 7
- Watchers: 8
- Forks: 6
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
*ServiceNow completed its acquisition of Element AI on January 8, 2021. All references to Element AI in the materials that are part of this project should refer to ServiceNow.*
# MiniTouch benchmark
Benchmark proposed and used in: Touch-based Curiosity for Sparse-Reward Tasks.
MiniTouch, a manipulation benchmark of simulated tasks is comprised of four manipulation tasks:
- Pushing
- Opening
- Picking
- Playing with simple objects
It allows evaluation of models' performance on different manipulation tasks that can leverage cross-modal learning.
## How to install
Clone the repository then:
```bash
cd minitouch
pip install -e .
```
## Quick Start
```python
import minitouch.env
import gym
env = gym.make("Pushing-v0")
state = env.reset()
for i in range(0, 1000):
state, reward, done, info = env.step(env.action_space.sample())
```
## Available tasks
- Pushing-v0
- Opening-v0
- Picking-v0
- Playing-v0
Note: If you want to see the GUI of the environment you have to use the
debug version of the environment. For example use "PushingDebug-v0" instead of
"Pushing-v0".