StanfordASL/ALPaCA

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

Jupyter Notebook

6 commits

updated Feb 15, 2023

See the code

README

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.

Running the code

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

Contributors

apoorva-sharma

4 commits

jmesharrison

2 commits

Similar repos

openai/grok

4,259

lm-playpen/playpen-paper-2025

Code for reproducing the results reported in (Horst et al., 2025)

Clara-X/ReproAlphaRL

alexub/jax-meta-learning

Simple, extensible implementations of some meta-learning algorithms in Jax

google/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

10,914

edwardmilsom/pion_authorcode_reproducing

Sweeping learning rate for the Pion Libera Object experiment, using their own experiment code as…

Tiime-Software/IMABO

IMABO: an infinitely many-armed bandit with an oracle, for hyperparameter optimization at inference…

vimarsh/repro-costaware-stopping-bayesopt

Space

Repro - Cost-aware Stopping for Bayesian Optimization

Languages

Jupyter Notebook

70.9%

Python

28.9%

StanfordASL/ALPaCA

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

Jupyter Notebook

6 commits

updated Feb 15, 2023

See the code

README

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.

Running the code

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

Similar repos

openai/grok

4,259

lm-playpen/playpen-paper-2025

Code for reproducing the results reported in (Horst et al., 2025)

Clara-X/ReproAlphaRL

alexub/jax-meta-learning

Simple, extensible implementations of some meta-learning algorithms in Jax

google/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

10,914

edwardmilsom/pion_authorcode_reproducing

Sweeping learning rate for the Pion Libera Object experiment, using their own experiment code as…

Tiime-Software/IMABO

IMABO: an infinitely many-armed bandit with an oracle, for hyperparameter optimization at inference…

vimarsh/repro-costaware-stopping-bayesopt

Space

Repro - Cost-aware Stopping for Bayesian Optimization

Contributors

apoorva-sharma

4 commits

jmesharrison

2 commits

Languages

Jupyter Notebook

70.9%

Python

28.9%