Skip to main content

OpenAI Gym-compatible implementation of a simple memory-testing environment.

Project description

SimpleMemoryTestingEnv

This is a simple OpenAI Gym-compatible environment to test RL agent's memory.

Usage

gym must be installed. Environments can be created as follows:

>>> import gym
>>> import simple_memory_testing_env
>>> env = gym.make("SimpleMemoryTestingEnv-v0")
  • default environment (partial observability + memory-requiring T-maze with 4 different colors) : "SimpleMemoryTestingEnv-v0" (with only 2 colors: "SimpleMemoryTestingEnv-2Colors-v0")

default_env

  • easy environment (partial observability maze with 4 different colors) : "SimpleMemoryTestingEnv-Easy-v0" (with only 2 colors: "SimpleMemoryTestingEnv-Easy-2Colors-v0")

easy_env

Installation

Installing via pip

This package is available in PyPi as simple_memory_testing_env

pip install simple_memory_testing_env

Installing via cloning this repository

git clone https://www.github.com/Near32/SimpleMemoryTestingEnv
cd SimpleMemoryTestingEnv
pip install -e .

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

simple_memory_testing_env-0.0.1.tar.gz (5.3 kB view hashes)

Uploaded Source

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