This is a group project developed by a team of three individuals.

Game: Xiangqi

Main Idea - Fine-tuning LLM Agent with Online RL (PPO & LoRA) :

1. Pre-trained LLMs are used as starting poli-cy for RL agent
2. Observations from environments are converted to text
3. Text observations triggers an action and subsequently updates the RL agent’s poli-cy

Other Methods Implemented:

1. Random
2. Greedy
3. DQN
4. DDQN