lucasbertola Goto Github PK

alphazero

Discover our groundbreaking implementation of DeepMind's Alpha Zero, a self-learning AI algorithm inspired by AlphaGo. Witness superhuman performance in board games and explore its incredible capabilities!

connect-4-gym-env-reinforcement-learning

Connect Four Environment is a project designed for training reinforcement learning models to play the classic Connect4 game. It's compatible with OpenAI Gym / Gymnasium, includes a variety of bots, an Elo leaderboard system, and supports both FCN and CNN policies.

double-conversion-decimal-binary

Efficient binary-decimal and decimal-binary conversion routines. u int8 /u int16 /u int32 / float16 / float34 / to binary string or Array Binary. Can invert operation. Use IEEE 754 - 1985

gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

http-client

Http client in c++

minigrid-env

MiniGrid is a customizable reinforcement learning environment where agents navigate a grid to reach a target. Compatible with FCN and CNN policies, it offers real-time human render mode and follows the OpenAI Gym / Gymnasium interface. Includes detailed documentation, examples, and tests.

node-parallel-http

Async parallel HTTP / HTTPS requests in NodeJs. HTTP / HTTPS / SOCKS5 / TOR NETWORK / BRUTEFORCE

quoridor_env

wsa-web-socket-asynchrone

Web Socket Asynchrone client for C++