bryanoliveira
Passionate computer scientist working towards artificial general intelligence through deep & reinforcement learning research.
@dlb-rlBrasil
Pinned Repositories
bone-age-regression
A Deep Learning approach to solve the bone age regression problem.
cellular-automata
A cellular automata program built with C++, OpenGL, CUDA and OpenMP.
cpp-pdf2txt
A PDF to text converter using a MLP-based OCR.
habla
A coding assistant for entire codebases.
PY-VSSS-INF
Python implementation of IEEE Very Small Sizer Soccer by Pequi Mecânico INF team version
python-availability-bot
A Python bot that checks a list of sites for product availability and sends alerts via webhooks.
sliding-puzzles-gym
A scalable benchmark for state representation learning in visual reinforcement learning.
soccer-twos-env
A Python package to wrap a compiled soccer-twos reinforcement learning environment with gym-compatible interfaces.
unity-soccer
unity-zombit
A Unity3D, multiplatform, retro wave top-down shooter with addictive gameplay.
bryanoliveira's Repositories
bryanoliveira/soccer-twos-env
A Python package to wrap a compiled soccer-twos reinforcement learning environment with gym-compatible interfaces.
bryanoliveira/habla
A coding assistant for entire codebases.
bryanoliveira/cellular-automata
A cellular automata program built with C++, OpenGL, CUDA and OpenMP.
bryanoliveira/python-availability-bot
A Python bot that checks a list of sites for product availability and sends alerts via webhooks.
bryanoliveira/unity-soccer
bryanoliveira/omnimeter
A hardware resource monitor that sends info from Windows & Linux to a Flutter app.
bryanoliveira/wtf
WhatsApp Toolbox Features - Chrome Extension that allows you to send WhatsApp messages in bulk
bryanoliveira/xml2conll
A simple script to convert XML Named Entity Recognition annotations to the CONLL format.
bryanoliveira/raindrop-search-extension
Adds a sidebar to google search with results from your raindrop saves.
bryanoliveira/sliding-puzzles-gym
A scalable benchmark for state representation learning in visual reinforcement learning.
bryanoliveira/spgym-experiments
bryanoliveira/whisper_torchserve
Torchserve build for Whisper-Speech to text model.
bryanoliveira/ArCHer
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
bryanoliveira/auto-sports-narrator
I play with my best friend GPT
bryanoliveira/bento2seldon4recsys
bryanoliveira/bryanoliveira
My Github profile's README.
bryanoliveira/bryanoliveira.github.io
My personal website.
bryanoliveira/cabrita
Finetuning InstructLLaMA with portuguese data
bryanoliveira/databerry
The no-code platform for building custom LLM Agents
bryanoliveira/dmcontrol-generalization-benchmark
DMControl Generalization Benchmark
bryanoliveira/docker-push-ssh
Push docker images from your local machine to remote servers without the hassle.
bryanoliveira/dreamerv3
Mastering Diverse Domains through World Models
bryanoliveira/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
bryanoliveira/gfootball
bryanoliveira/hashmap-experiments
bryanoliveira/multiturn-benchmark
bryanoliveira/rl-teacher
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
bryanoliveira/soccer-twos-starter
Example training/testing scripts for our soccer-twos-env.
bryanoliveira/undergraduate-thesis
[LaTeX] Intrinsic motivation for robotic manipulation learning with sparse rewards
bryanoliveira/workload-daemon