Projeto de tcc que traz a ideia de uma academia online

RL for Type-1 Diabetes Control

🛒 Sistema de pedidos em TypeScript usando POO e arquitetura orientada a eventos (projeto da Unidade 4).

Fine-tunes FLAN-T5 using Reinforcement Learning (PPO) and PEFT to generate less toxic summaries, leveraging Meta AI's hate speech reward model for detoxification.

Hybrid Reinforcement Learning and minimax agent for Tablut game. Combines PPO trained value networks with alpha beta search for competitive play.

Comparing the performance of MPC based racing and RL based racing

Data Center Environment and Reinforcement Learning (RL) Control