Skip to content

README.md

Latest commit

 

History

History
15 lines (11 loc) · 1.08 KB

README.md

File metadata and controls

15 lines (11 loc) · 1.08 KB

Reinforcement-Learning 🤖

  1. frozen-lake-model_free: Solving the frozen Lake (non-slippery) environment using:

    • Monte Carlo
    • SARSA
    • Epsilon-Greedy SARSA

  2. space-invaders-dqn:
    This folder contains the basic setup for a DQN agent for the Space Invaders environment.

  3. space-invaders-double-dqn:
    This folder features a Double DQN implementation for the Space Invaders game. It performs better than a single-Q network and converges faster too.

  4. car-racing-double-dqcnn:
    This folder contains the implementation of a Double DQCNN (Deep Q-Convolutional Neural Network) agent for the Car Racing environment. The agent is still struggling to learn effectively so some minor bugs need to be fixed.