This repository contains implementations of various Reinforcement Learning (RL) algorithms for the ConnectX game. These implementations showcase different approaches to training an AI agent to play efficiently.
- Proximal Policy Optimization (PPO)
- Deep Q-Learning (DQN)
- Minimax Algorithm
- Dynamic Rewards for RL Training
Each implementation provides insights into the training process and strategies for decision-making in ConnectX.
Explore, experiment, and enhance these models to improve their performance in ConnectX!