dhruvsreenivas / gym-simplifiedtetris

🟥 Simplified Tetris environments compliant with OpenAI Gym's API

Gym-SimplifiedTetris

Report Bug · Request Feature · Suggestions

---

🟥 Simplified Tetris environments compliant with OpenAI Gym's API

Gym-SimplifiedTetris is a pip installable package that creates simplified Tetris environments compliant with OpenAI Gym's API. Gym's API is the field standard for developing and comparing reinforcement learning algorithms.

There are currently three agents and 64 environments provided. The environments are simplified because the player must select the column and piece's rotation before the piece starts falling vertically downwards. If one looks at the previous approaches to the game of Tetris, most of them use this simplified setting.

---

• 1. Installation
• 2. Usage
• 3. Future work
• 4. Acknowledgements

1. Installation

The package is pip installable:

pip install gym-simplifiedtetris

Or, you can copy the repository by forking it and then downloading it using:

git clone https://github.com/<YOUR-USERNAME>/gym-simplifiedtetris

Packages can be installed using pip:

cd gym-simplifiedtetris
pip install -r requirements.txt

2. Usage

The file examples/envs.py shows two examples of using an instance of the simplifiedtetris-binary-20x10-4-v0 environment for ten games. You can create an environment using gym.make, supplying the environment's ID as an argument.

import gym
import gym_simplifiedtetris

env = gym.make("simplifiedtetris-binary-20x10-4-v0")
obs = env.reset()

# Run 10 games of Tetris, selecting actions uniformly at random.
episode_num = 0
while episode_num < 10:
    env.render()
    
    action = env.action_space.sample()
    obs, reward, done, info = env.step(action)

    if done:
        print(f"Episode {episode_num + 1} has terminated.")
        episode_num += 1
        obs = env.reset()

env.close()

Alternatively, you can import the environment directly:

from gym_simplifiedtetris import SimplifiedTetrisBinaryEnv as Tetris

env = Tetris(grid_dims=(20, 10), piece_size=4)

3. Future work

• Normalise the observation spaces.
• Implement an action space that only permits the agent to take non-terminal actions.
• Implement more shaping rewards: potential-style, potential-based, dynamic potential-based, and non-potential. Optimise their weights using an optimisation algorithm.
• Write end-to-end and integration tests using pytest.
• Perform mutation and property-based testing using mutmut and Hypothesis.
• Use Coverage.py to increase code coverage.

4. Acknowledgements

This package utilises several methods from the codebase developed by andreanlay (2020) and the codebase developed by Benjscho (2021).