pyrace 0.0.11

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

pyrace

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

Import

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.