MABEL

MAnipulation BEnchmarks for Learning

MABEL is a collection of environments/tasks for benchmarking manipulation, simulated with the Mujoco physics engine and wrapped in the OpenAI gym API. 'MABEL' constains following tasks

Pointing | Pouring | Relocation | Zipping :-------------------------:|:-------------------------:|:-------------------------:|:-------------------------: | | |

Getting Started

MABEL uses git submodules to resolve dependencies. Please follow steps exactly as below to install correctly.

0. Ensure you have access these repositories - Franka_sim, Furniture_sim and Scene_sim

1. Clone this repo with pre-populated submodule dependencies

$ git clone --recursive git@github.com:vikashplus/mabel.git

2. Update submodules

$ cd mabel  
$ git submodule update --remote

3. Add repo to pythonpath by updating ~/.bashrc or ~/.bash_profile

export PYTHONPATH="<path/to/mabel>:$PYTHONPATH"

4. Follow install instructions from mjrl to get model free agents for MABEL
5. To visualize an env using a random policy

MJPL python mabel/mabel_agents/mjrl/examine_policy.py -i mabel -e MableReachRandom-v0

5. To visualize a trained mjrl agent's policy

MJPL python mabel/mabel_agents/mjrl/examine_policy.py -i mabel -e MableReachRandom-v0 -p <path to policy>