Create base class for Environment - Githubissues

UFRN-URNAI / urnai-tools

A modular Deep Reinforcement Learning library that supports multiple environments, made with Python 3.6.

Apache License 2.0

5 stars 8 forks source link

Create base class for Environment #66

Closed alvarofpp closed 7 months ago

alvarofpp commented 9 months ago

Following the package standard for DRL, we need the class to have the following methods:

start: Starts the environment.
step: Executes an action in the environment, and returns a tuple of [Observation, Reward, Done].
reset: Resets the environment and returns an Observation.
close: Closes the environment.

Suggestions:

Class name: EnvironmentBase.
Class path: urnai.environments.
Source: https://github.com/UFRN-URNAI/urnai-tools/blob/main/urnai/envs/base/abenv.py .

Notes:

This is an abstract class, so it is important that it inherits from abc.ABC.
You don't need the Savable class.