https://github.com/openai/mlsh
Code for the paper "Meta-Learning Shared Hierarchies"
https://github.com/openai/mlsh
paper
Last synced: 2 months ago
JSON representation
Code for the paper "Meta-Learning Shared Hierarchies"
- Host: GitHub
- URL: https://github.com/openai/mlsh
- Owner: openai
- Created: 2017-10-26T06:47:59.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2023-07-06T21:08:25.000Z (almost 2 years ago)
- Last Synced: 2025-03-28T13:10:05.607Z (3 months ago)
- Topics: paper
- Language: Python
- Homepage: https://arxiv.org/abs/1710.09767
- Size: 403 KB
- Stars: 611
- Watchers: 43
- Forks: 162
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
**Status:** Archive (code is provided as-is, no updates expected)
# Meta-Learning Shared Hierarchies
Code for [Meta-Learning Shared Hierarchies](https://s3-us-west-2.amazonaws.com/openai-assets/MLSH/mlsh_paper.pdf).
##### Installation
```
Add to your .bash_profile (replace ... with path to directory):
export PYTHONPATH=$PYTHONPATH:/.../mlsh/gym;
export PYTHONPATH=$PYTHONPATH:/.../mlsh/rl-algs;
Install MovementBandits environments:
cd test_envs
pip install -e .
```
##### Running Experiments
```
python main.py --task AntBandits-v1 --num_subs 2 --macro_duration 1000 --num_rollouts 2000 --warmup_time 20 --train_time 30 --replay False AntAgent
```
Once you've trained your agent, view it by running:
```
python main.py [...] --replay True --continue_iter [your iteration] AntAgent
```
The MLSH script works on any Gym environment that implements the randomizeCorrect() function. See the envs/ folder for examples of such environments.
To run on multiple cores:
```
mpirun -np 12 python main.py ...
```