A grid-like environment (multi-agent system) used by an intelligent agent (or more than one agent) in order for it/them to carry the orbs to the pits in a limited number of movements.
-
Updated
Jun 8, 2024 - Python
A grid-like environment (multi-agent system) used by an intelligent agent (or more than one agent) in order for it/them to carry the orbs to the pits in a limited number of movements.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF settings.
A collection of MARL benchmarks based on TorchRL
Multi-agent collaboration (2 UR10s) in Omniverse Isaac Gym/Sim.
A tool for aggregating and plotting MARL experiment data.
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.
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
A Sample Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning
Predator-Prey-Grass gridworld environment using PettingZoo, with dynamic deletion and spawning of partially observant agents.
Extended, multi-agent and multi-objective (MaMoRL) environments based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.
This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.
Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
无人机动态覆盖控制;1. 实现了一个无人机点覆盖环境;2. 给出了无人机连通保持规则;3. 给出了基于MARL的控制算法
Moss is a Python library for Reinforcement Learning.
A reinforcement learning cross attention channel with centralized training and execution for NMMO NeurIPS 2023
train AI agents to master Free-style Gomoku(五子棋)
stress testing black-box AVs with MARL
Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles
Add a description, image, and links to the marl topic page so that developers can more easily learn about it.
To associate your repository with the marl topic, visit your repo's landing page and select "manage topics."