Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
Updated
Jun 12, 2024 - Python
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
Predator-Prey-Grass gridworld environment using PettingZoo, with dynamic deletion and spawning of partially observant agents.
Autonomous driving agent in Carla simulator leveraging IL and RL techniques.
Rllib framework for using Unreal Engine 5 (UE5) as external environment for Reinforced Learning training process
Wrappers for reinforcement learning algorithms (i.e. stable baselines 3, RLlib) to work with pyRDDLGym.
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
Reinforcement learning algorithm that blends the N-th order Markov property with abstract MDPs, PPO, and a hybrid model-free/model-based approach.
Reinforcement learning algorithms in RLlib
An open, minimalist Gymnasium environment for autonomous coordination in wireless mobile networks.
Tutorial for Ray
Reinforcement Learning for Unmanned Airial Vehicles
A template for deploying DreamerV3 with Ray RLlib, compatible with Gym and custom environments.
An open source library for connecting AnyLogic models with Reinforcement Learning frameworks through OpenAI Gymnasium
Balloon Flight Custom Ray environment
β‘ β‘ ππ¦π¦π± ππ πππ¨π°π΅π³π’π₯πͺπ―π¨ πΈπͺπ΅π© ππ’πΊ πππ
A minimalist multi-agent implementation of the social dilemma problem with governance kernels
Construction of controllers for Shadow-Hand in Mujoco environment, using Deep Learning. 2 Different methods were used to create the controllers: a) Behavioral Cloning b) Deep Reinforcement Learning
Multi-agent Reinforcement Learning project to train agents to extinguish fire in a 2D grid world. Uses Ray RLlib (2.6.1).
Add a description, image, and links to the rllib topic page so that developers can more easily learn about it.
To associate your repository with the rllib topic, visit your repo's landing page and select "manage topics."