Adapting to unseen partners in multi-agent Reinforcement Learning (MARL) using Evolutionary Strategies (ES).
-
Updated
Sep 22, 2022 - Jupyter Notebook
Adapting to unseen partners in multi-agent Reinforcement Learning (MARL) using Evolutionary Strategies (ES).
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.
Ensuring trust among agents using Multi-Agent Deep Reinforcement Learning
The proceedings of top conference in 2021 on the topic of Reinforcement Learning (RL), including: AAAI, IJCAI, NeurIPS, ICML, ICLR, ICRA, AAMAS and more.
Studying emergent communication among agents in cooperative and competitive environments using Reinforcement Learning, game theory and replicator dynamics
Unity로 멀티 에이전트 강화학습(MARL) 수행하기 위한 프레임 워크 제공
Pytorch implementation of MADDPG algorithm
This is one component of Cross-functional Team-based Multi-agent (CTMA) framework.
stress testing black-box AVs with MARL
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.
Team-based Multi-agent Reinforcement Learning
Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles
train AI agents to master Free-style Gomoku(五子棋)
Exploring techniques to generate diverse conventions in multi-agent settings
Moss is a Python library for Reinforcement Learning.
A multi agent reinforcement learning environment where two agents controlled by DRQNs play a custom version of the pursuit-evasion game.
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."