Marcus Loo Vergara's repositories
Carla-ppo
This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
HoverLookup_ChromeExtension
Google Chrome extension. Press <CTRL> + <SHIFT> while hovering over a word will show the wiktionary entry for that word in an inline window.
RoadFollowing-ddpg
Using DDPG with a VAE feature extractor to train a car to follow a road from a top-down perspective (modified version of CarRacing-v0)
OverworldGame
Overworld is a 2D tile-based sandbox game
CarRacing-v0-ppo
Solving CarRacing-v0 with Proximal Policy Gradient
Keypoint_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
UnrealTemples
A small action RPG with temples to explore and enemies to beat. Made in Unreal Engine 4.
GGJ16_Holmgang
Global Game Jam 2016: Holmgang
RoadFollowing-ppo
Training a car in a modified CarRacing-v0 environment to follow the road in ~15 episodes
Computer_Vision_Project
Training a Faster R-CNN to recognize the 5 classes from the udacity dataset 2
lightweight-firestore-cpp
Lightweight C++ class that wraps Firestore RPC communication into a simple interface.
Spotlight-Desktop
Simple app to change the desktop wallpaper to the Windows Spotlight Lock Screen image.
VulkanComputeSamples-Transposition
Sample code for matrix transposition in Vulkan
webgpu-cross-platform-demo
Barebones demo of WebGPU cross-platform (web/native) via CMake/Emscripten
WebGPU-distribution
Distributions of WebGPU for native and web development, easy to integrate and interchangeable.