Multi-Agent Reinforcement Learning - Groups

Half Field Offense

The Half Field Offense environment is a multi-agent reinforcement learning problem where multiple agents interact in a soccer-like environment.

Dataset
JSON

Multi-Team Predator-Prey

The Multi-Team Predator-Prey environment is a multi-agent reinforcement learning problem where multiple predators and prey interact in a grid-based environment.

Dataset
JSON

COLLECT

The authors used a multi-agent grid-world game called COLLECT, where four agents can move and collect coins of different colors.

Dataset
JSON

COGMENT

The proposed solution is divided into two main components: leverage human-MARL teaming framework, called COGMENT, to handle the collaboration between human and multiple RL-based...

Dataset
JSON

StarCraft II micromanagement tasks

The dataset used in the paper is the StarCraft II micromanagement tasks.

Dataset
JSON

MADDPG dataset

The dataset used in this paper is a set of nine MARL tasks across two environments, with a focus on co-operative contexts.

Dataset
JSON

Multi-Agent Particle Environment and Google Research Football Environment

Multi-agent particle environment and Google Research football environment.

Dataset
JSON

ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

Modern multi-agent reinforcement learning frameworks rely on centralized training and reward shaping to perform well. However, centralized training and dense rewards are not...

Dataset
JSON

Google Research Football

The Google Research Football environment is a reinforcement learning experimental platform focused on training agents to play football.

Dataset
JSON

Multi-Agent Particle Environment

The Multi-Agent Particle Environment is a medium-size collaborative problem where a defensive escort team of agents is learning to maintain an optimal formation around the VIP...

Dataset
JSON

Defensive Escort Team Problem

The defensive escort team problem is a challenging dual-reward collaborative MARL problem where a group of learning agents have to simultaneously learn to maximize the...

Dataset
JSON

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Multi-agent environments for training and testing the proposed Multi-Agent Actor-Critic (MAAC) algorithm.

Dataset
JSON

32 datasets found