XanderJC

scalable-birl

Scalable Bayesian Inverse Reinforcement Learning (ICLR 2021) by Alex J. Chan and Mihaela van der Schaar.

medkit-learn

The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation (NeurIPS 2021) by Alex J. Chan, Ioana Bica, Alihan Huyuk, Daniel Jarrett, and Mihaela van der Schaar.

attention-based-credit

Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Preferences

transductive-dropout

Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift (ICML 2020) by Alex J. Chan, Ahmed M. Alaa, Zhaozhi Qian, and Mihaela van der Schaar.

synthetic-model-combination

Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning (NeurIPS 2022) by Alex J. Chan and Mihaela van der Schaar.

inverse-online

Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies (ICLR 2022) by Alex J. Chan, Alicia Curth, and Mihaela van der Schaar.

XanderJC.github.io

Personal website

AML_bayes_opt

Supporting code for the Advanced Machine Learning module, MPhil Machine Learning and Machine Intelligence

data_collection

llm-articulation

MCMC-Project

Code for my project comparing theoretical bounds with practical convergence diagnostics in MCMC.

my-cookiecutter

My cookiecutter template for ML projects

deepspeed_llama

Finetuning LLaMA with DeepSpeed

mphil-thesis

Supplementary code for my MPhil thesis.

rnn-handwriting-generation

Handwriting generation by RNN with TensorFlow, based on "Generating Sequences With Recurrent Neural Networks" by Alex Graves

RowingManager

trl

Train transformer language models with reinforcement learning.

TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

XanderJC

Config files for my GitHub profile.