All Projects → DerwenAI → gym_example

DerwenAI / gym_example

Licence: MIT license
An example implementation of an OpenAI Gym environment used for a Ray RLlib tutorial

Programming Languages

python
139335 projects - #7 most used programming language
Jupyter Notebook
11667 projects

Projects that are alternatives of or similar to gym example

a-minimalist-guide
Walkthroughs for DSL, AirSim, the Vector Institute, and more
Stars: ✭ 37 (+48%)
Mutual labels:  ray, rllib
ray tutorial
An introductory tutorial about leveraging Ray core features for distributed patterns.
Stars: ✭ 67 (+168%)
Mutual labels:  ray, rllib
Ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
Stars: ✭ 18,547 (+74088%)
Mutual labels:  ray, rllib
stadium
A graphical interface for reinforcement learning and gym-based environments. Integrates tensorboard and various configuration utilities for ease of usage.
Stars: ✭ 26 (+4%)
Mutual labels:  gym-environment
Neural-Fictitous-Self-Play
Scalable Implementation of Neural Fictitous Self-Play
Stars: ✭ 52 (+108%)
Mutual labels:  gym-environment
2048-Gym
This projects aims to use reinforcement learning algorithms to play the game 2048.
Stars: ✭ 68 (+172%)
Mutual labels:  gym-environment
Horovod
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Stars: ✭ 11,943 (+47672%)
Mutual labels:  ray
mgym
A collection of multi-agent reinforcement learning OpenAI gym environments
Stars: ✭ 41 (+64%)
Mutual labels:  gym-environment
Multi-Commander
Multi & Single Agent Reinforcement Learning for Traffic Signal Control Problem
Stars: ✭ 67 (+168%)
Mutual labels:  ray
torchx
TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and support for E2E production ML pipelines when you're ready.
Stars: ✭ 165 (+560%)
Mutual labels:  ray
distributedRL
A framework for easy prototyping of distributed reinforcement learning algorithms
Stars: ✭ 93 (+272%)
Mutual labels:  ray
app
Buggregator is a beautiful, lightweight debug server build on Laravel that helps you catch your smpt, sentry, var-dump, monolog, ray outputs. It runs without installation on multiple platforms.
Stars: ✭ 259 (+936%)
Mutual labels:  ray
node-ray
Debug your NodeJS & web code with Ray to fix problems faster
Stars: ✭ 39 (+56%)
Mutual labels:  ray
codeflare
Simplifying the definition and execution, scaling and deployment of pipelines on the cloud.
Stars: ✭ 163 (+552%)
Mutual labels:  ray
malib
A parallel framework for population-based multi-agent reinforcement learning.
Stars: ✭ 341 (+1264%)
Mutual labels:  ray
MuJoCo RL UR5
A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.
Stars: ✭ 108 (+332%)
Mutual labels:  gym-environment
kuberay
A toolkit to run Ray applications on Kubernetes
Stars: ✭ 146 (+484%)
Mutual labels:  ray
Mars
Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
Stars: ✭ 2,308 (+9132%)
Mutual labels:  ray
Modin
Modin: Speed up your Pandas workflows by changing a single line of code
Stars: ✭ 6,639 (+26456%)
Mutual labels:  ray
GPU-Pathtracer
GPU Raytracer from scratch in C++/CUDA
Stars: ✭ 326 (+1204%)
Mutual labels:  ray

gym_example

Example implementation of an OpenAI Gym environment, to illustrate problem representation for RLlib use cases.

Usage

Clone the repo and connect into its top level directory.

To initialize and run the gym example:

pip install -r requirements.txt
pip install -e gym-example

python sample.py

To run Ray RLlib to train a policy based on this environment:

python train.py

Kudos

h/t:

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].