Skip to main content

This package provides an environment to practice different types of reingorcement learning models.

Project description


This library provides a flexible environment to practice different Reinforcment learning models.


from pyrace import Env

Creat an environment

env = Env()

Env class

The methods of this class are pretty similar to the environments provided by the gym library.
render : print an image of the current state of the environment. please make sure to turn the backend of matplotlib to auto (%matplotlib Auto)
reset : reset the environment and output tu initial state.
step : takes an action as input. An action is an array, the size and types in this array are defined by the environment's action space.This method outputs the new state.
load : Input the name of a map and it reset the environment with this new map loaded. Currently only one map is ready (map_1).So, this method is not that useful currently.
sample_action : no input, it output a random sample of the current environement's action space.
get_model_info : print the current environment's metadata. This metadata gives a description of the action space and the observation space.
get_model_list : gives the list of the names of the different available models.
get_map_list : gives the list of the names of the maps available.

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

pyrace-0.0.14.tar.gz (242.2 kB view hashes)

Uploaded source

Built Distribution

pyrace-0.0.14-py3-none-any.whl (244.4 kB view hashes)

Uploaded py3

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