ddqn-agents

FinSearch Research Competition

Fine-tuning LLM agents w online RL for XiangQi (Chinese Chess)

This project aims to build a smart energy management grid system to reduce the avg peak demand during peak hours. It uses CityLearn environment.

This repository contains the reinforcement learning framework for training a 2D car agent to navigate dynamically evolving obstacle courses, developed as a final project for the Reinforcement Learning course (academic year 24/25).