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"
)
- easy environment (partial observability maze with 4 different colors) :
"SimpleMemoryTestingEnv-Easy-v0"
(with only 2 colors:"SimpleMemoryTestingEnv-Easy-2Colors-v0"
)
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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Close
Hashes for simple_memory_testing_env-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1282ab830d37b275516410651cf81312af7efb24229e42c03bc291c5cd9c0eb8 |
|
MD5 | a7d6e47ad9f2163c397be273a39776e0 |
|
BLAKE2b-256 | ccf96f475301de5ce9cfdbdca76fc636d43b08b9b89b186af112ca6161a6760e |