Greeting! 👨‍💻

This place is where I document a few things I’ve learned.

Model-based RL with latent variable models

Model-based RL methods that learn latent-variable models instead of trying to predict dynamics models in the observed space. The learned world model then can be used in planning effectively rather than being less efficiently, for instance in visual-based tasks, generating images for future time steps and feed them back into the model to predict the next ones, which requires more computation. ...

September 22, 2024 · 19 min · Trung H. Nguyen

Graph generation with predefined chromatic number

Generating predefined-chromatic-number graphs with Leighton’s algorithm. ...

May 19, 2024 · 2 min · Trung H. Nguyen

Variational Autoencoder

An autoencoder that differs from others (with deterministic encoder) by mapping each input $\mathbf{x}$ to a distribution over the possible values of the latent representation $\mathbf{z}$ from which $\mathbf{x}$ could have been generated. ...

April 30, 2024 · 5 min · Trung H. Nguyen

Graph Representation Learning

April 16, 2024 · 9 min · Trung H. Nguyen

MuZero

January 2, 2024 · 6 min · Trung H. Nguyen

AlphaGo, AlphaGo Zero, AlphaZero

Model-based RL methods that use Monte Carlo Tree Search for planning and ultilize self-play mechanism for training. ...

October 17, 2023 · 11 min · Trung H. Nguyen

Multi-agent Deep Deterministic Policy Gradient

May 25, 2023 · 5 min · Trung H. Nguyen