ALPaCA

Code for "Meta-Learning Priors for Efficient Online Bayesian Regression" by James Harrison, Apoorva Sharma, and Marco Pavone

Installation

To install requirements, run

pip install -r requirements.txt

MuJoCo is required for Hopper experiment.

The experiments presented in the paper can be run from the jupyter notebooks.

Name		Name	Last commit message	Last commit date
configs		configs
data		data
figures		figures
gym		gym
main		main
maml		maml
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
hand_plotting.py		hand_plotting.py
hopper.ipynb		hopper.ipynb
lane-change.ipynb		lane-change.ipynb
multistep-varying-noise.ipynb		multistep-varying-noise.ipynb
multistep.ipynb		multistep.ipynb
pendulum.ipynb		pendulum.ipynb
predict_trajectory.ipynb		predict_trajectory.ipynb
predict_trajectory_quickdraw.ipynb		predict_trajectory_quickdraw.ipynb
requirements.txt		requirements.txt
sinusoid-varying-noise.ipynb		sinusoid-varying-noise.ipynb
sinusoid.ipynb		sinusoid.ipynb