https://github.com/vikashplus/mpl
https://github.com/vikashplus/mpl
Last synced: 11 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/vikashplus/mpl
- Owner: vikashplus
- License: apache-2.0
- Created: 2019-12-25T20:28:17.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2020-01-17T00:04:53.000Z (over 5 years ago)
- Last Synced: 2024-12-25T14:43:06.226Z (5 months ago)
- Language: Python
- Size: 160 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# MPL
`MPL` is a collection of environments/tasks using MPL system from APL, simulated with the [Mujoco](http://www.mujoco.org/) physics engine and wrapped in the OpenAI `gym` API.
## Getting Started
`MPL` uses git submodules to resolve dependencies. Please follow steps exactly as below to install correctly.
0. Ensure you have access these two repositories - [MPL](https://github.com/vikashplus/MPL) and [MPL_sim](https://github.com/vikashplus/MPL_sim.git).
1. Clone this repo with pre-populated submodule dependencies
```
$ git clone --recursive https://github.com/vikashplus/MPL.git
```
2. Update submodules
```
$ cd MPL
$ git submodule update --remote
```
3. Add repo to pythonpath by updating `~/.bashrc` or `~/.bash_profile`
```
export PYTHONPATH=":$PYTHONPATH"
```
4. Follow install instructions from [mjrl](https://github.com/aravindr93/mjrl) to get model free agents for `MPL'
5. To visualize an env using a random policy
```
python MPL_agents/mjrl/examine_policy.py -e SallyReachRandom-v0
```
5. To visualize an trained policy
```
python MPL_agents/mjrl/examine_policy.py -e SallyReachRandom-v0 -p MPL_agents/mjrl/sallyReachRandom-v0/best_policy.pickle
```