Skip to main content

Super Mario Bros. for OpenAI Gym

Project description

gym-super-mario-bros

BuildStatus PackageVersion PythonVersion Stable Format License

Mario

An OpenAI Gym environment for Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The Nintendo Entertainment System (NES) using the nes-py emulator.

Installation

The preferred installation of gym-super-mario-bros is from pip:

pip install gym-super-mario-bros

Usage

Python

You must import gym_super_mario_bros before trying to make an environment. This is because gym environments are registered at runtime. By default, gym_super_mario_bros environments use the full NES action space of 256 discrete actions. To contstrain this, gym_super_mario_bros.actions provides three actions lists (RIGHT_ONLY, SIMPLE_MOVEMENT, and COMPLEX_MOVEMENT) for the nes_py.wrappers.JoypadSpace wrapper. See gym_super_mario_bros/actions.py for a breakdown of the legal actions in each of these three lists.

from nes_py.wrappers import JoypadSpace
import gym_super_mario_bros
from gym_super_mario_bros.actions import SIMPLE_MOVEMENT
env = gym_super_mario_bros.make('SuperMarioBros-v0')
env = JoypadSpace(env, SIMPLE_MOVEMENT)

done = True
for step in range(5000):
    if done:
        state = env.reset()
    state, reward, done, info = env.step(env.action_space.sample())
    env.render()

env.close()

NOTE: gym_super_mario_bros.make is just an alias to gym.make for convenience.

NOTE: remove calls to render in training code for a nontrivial speedup.

Command Line

gym_super_mario_bros features a command line interface for playing environments using either the keyboard, or uniform random movement.

gym_super_mario_bros -e <the environment ID to play> -m <`human` or `random`>

NOTE: by default, -e is set to SuperMarioBros-v0 and -m is set to human.

NOTE: SuperMarioBrosRandomStages-* support the --stages/-S flag for supplying the set of stages to sample from like -S 1-4 2-4 3-4 4-4.

Environments

These environments allow 3 attempts (lives) to make it through the 32 stages in the game. The environments only send reward-able game-play frames to agents; No cut-scenes, loading screens, etc. are sent from the NES emulator to an agent nor can an agent perform actions during these instances. If a cut-scene is not able to be skipped by hacking the NES's RAM, the environment will lock the Python process until the emulator is ready for the next action.

Environment Game ROM Screenshot
SuperMarioBros-v0 SMB standard
SuperMarioBros-v1 SMB downsample
SuperMarioBros-v2 SMB pixel
SuperMarioBros-v3 SMB rectangle
SuperMarioBros2-v0 SMB2 standard
SuperMarioBros2-v1 SMB2 downsample

Individual Stages

These environments allow a single attempt (life) to make it through a single stage of the game.

Use the template

SuperMarioBros-<world>-<stage>-v<version>

where:

  • <world> is a number in {1, 2, 3, 4, 5, 6, 7, 8} indicating the world
  • <stage> is a number in {1, 2, 3, 4} indicating the stage within a world
  • <version> is a number in {0, 1, 2, 3} specifying the ROM mode to use
    • 0: standard ROM
    • 1: downsampled ROM
    • 2: pixel ROM
    • 3: rectangle ROM

For example, to play 4-2 on the downsampled ROM, you would use the environment id SuperMarioBros-4-2-v1.

Random Stage Selection

The random stage selection environment randomly selects a stage and allows a single attempt to clear it. Upon a death and subsequent call to reset the environment randomly selects a new stage. This is only available for the standard Super Mario Bros. game, not Lost Levels (at the moment). To use these environments, append RandomStages to the SuperMarioBros id. For example, to use the standard ROM with random stage selection use SuperMarioBrosRandomStages-v0. To seed the random stage selection use the seed method of the env, i.e., env.seed(222), before any calls to reset. Alternatively pass the seed keyword argument to the reset method directly like reset(seed=222).

In addition to randomly selecting any of the 32 original stages, a subset of user-defined stages can be specified to limit the random choice of stages to a specific subset. For example, the stage selector could be limited to only sample castle stages, water levels, underground, and more.

To specify a subset of stages to randomly sample from, create a list of each stage to allow to be sampled and pass that list to the gym.make() function. For example:

gym.make('SuperMarioBrosRandomStages-v0', stages=['1-4', '2-4', '3-4', '4-4'])

The example above will sample a random stage from 1-4, 2-4, 3-4, and 4-4 upon every call to reset.

Step

Info about the rewards and info returned by the step method.

Reward Function

The reward function assumes the objective of the game is to move as far right as possible (increase the agent's x value), as fast as possible, without dying. To model this game, three separate variables compose the reward:

  1. v: the difference in agent x values between states
    • in this case this is instantaneous velocity for the given step
    • v = x1 - x0
      • x0 is the x position before the step
      • x1 is the x position after the step
    • moving right ⇔ v > 0
    • moving left ⇔ v < 0
    • not moving ⇔ v = 0
  2. s: the difference in agent's score values between frames
    • Encourages getting power ups and finishing the level faster
    • s = s0 - s1
      • s0 is the score before the step
      • s1 is the score after the step
  3. c: the difference in the game clock between frames
    • the penalty prevents the agent from standing still
    • c = c0 - c1
      • c0 is the clock reading before the step
      • c1 is the clock reading after the step
    • no clock tick ⇔ c = 0
    • clock tick ⇔ c < 0
  4. d: a death penalty that penalizes the agent for dying in a state
    • this penalty encourages the agent to avoid death
    • alive ⇔ d = 0
    • dead ⇔ d sets the entire reward to -15

r = v + s + c + d

The reward is clipped into the range (-15, 15).

info dictionary

The info dictionary returned by the step method contains the following keys:

Key Type Description
coins int The number of collected coins
flag_get bool True if Mario reached a flag or ax
life int The number of lives left, i.e., {3, 2, 1}
score int The cumulative in-game score
stage int The current stage, i.e., {1, ..., 4}
status str Mario's status, i.e., {'small', 'tall', 'fireball'}
time int The time left on the clock
world int The current world, i.e., {1, ..., 8}
x_pos int Mario's x position in the stage (from the left)
y_pos int Mario's y position in the stage (from the bottom)

Citation

Please cite gym-super-mario-bros if you use it in your research.

@misc{gym-super-mario-bros,
  author = {Christian Kauten},
  howpublished = {GitHub},
  title = {{S}uper {M}ario {B}ros for {O}pen{AI} {G}ym},
  URL = {https://github.com/Kautenja/gym-super-mario-bros},
  year = {2018},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gym_super_mario_bros_soumil-7.4.0.tar.gz (19.0 kB view hashes)

Uploaded Source

Built Distribution

gym_super_mario_bros_soumil-7.4.0-py3-none-any.whl (19.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page