README.md

metadata

license: mit
language:
  - en
tags:
  - Atari-Breakout-v0
  - deep-reinforcement-learning
  - reinforcement-learning
model-index:
  - name: Deep Q Learning
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Atari-Breakout-v0
          type: Atari-Breakout-v0
        metrics:
          - type: mean_reward
            value: 29
            name: mean_reward
            verified: false

Deep Q-Learning based Agent for Atari Breakout

The agent showcased in this space is trained using the Deep Q-Learning algorithm. The agent was trained for $3500$ episodes with a learning rate of $0.00001$ and an epsilon value that decreased linearly over time.

Usage

python main.py --model_folder <Name of the folder> --model_name <Name of the model> --save_video 1 --video_name <Name of the video file>