🚀 LunarLander DQN Agent
This model was trained using Deep Q-Networks (DQN) to solve the LunarLander-v2 environment.
🧠 Model
- Algorithm: Deep Q-Network (DQN)
- Framework: PyTorch
- Environment: LunarLander-v2
📂 Files
- dqn_lunarlander.pt → trained model
- lunarlander_dqn.gif → performance demo
🎯 Goal
Train an agent to land safely between flags.
📊 Result
Agent successfully learns stable landing behavior.
