This repository contains code for implementing reinforcement learning using the SpaceInvaders-v0 environment from the OpenAI Gym.
To run this code, you need the following dependencies:
- Python 3.x
- Gym:
pip install gym - TensorFlow:
pip install tensorflow - Keras-RL2:
pip install keras-rl2
- Clone the repository:
git clone https://github.com/your_username/your_repository.git - Navigate to the cloned repository:
cd your_repository
- Open the Python script
space_invaders_rl.py. - Configure the number of episodes and other parameters as needed.
- Run the script:
python space_invaders_rl.py.
The code performs the following steps:
- Imports the necessary libraries and initializes the SpaceInvaders-v0 environment.
- Runs a specified number of episodes, where each episode represents a game.
- Resets the environment for each episode and plays the game until completion.
- Renders the environment to visualize the game.
- Uses a random policy to select actions.
- Accumulates the score and prints the episode number and score.
- Closes the environment after all episodes have been completed.
- Builds a convolutional neural network model using Keras.
- Implements the DQN agent using the Keras-RL2 library.
- Compiles the agent with the Adam optimizer.
- Trains the agent on the SpaceInvaders-v0 environment.
- Tests the trained agent on a few episodes and calculates the average score.
- Saves the trained weights of the DQN agent.
- Loads the saved weights of the DQN agent.
Feel free to modify and adapt this code according to your needs.