18 papers with code • 0 benchmarks • 0 datasets

The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.


Greatest papers with code

mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions

mlr-org/mlr 9 Mar 2017

We present mlrMBO, a flexible and comprehensive R toolbox for model-based optimization (MBO), also known as Bayesian optimization, which addresses the problem of expensive black-box optimization by approximating the given objective function through a surrogate regression model.


Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

oxwhirl/pymarl 19 Mar 2020

At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and communication constraints are lifted.

SMAC Starcraft

The StarCraft Multi-Agent Challenge

oxwhirl/pymarl 11 Feb 2019

In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap.

SMAC Starcraft +1

Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning

hijkzzz/pymarl2 6 Feb 2021

Multi-Agent Reinforcement Learning (MARL) has seen revolutionary breakthroughs with its successful application to multi-agent cooperative tasks such as computer games and robot swarms.

SMAC Starcraft

FACMAC: Factored Multi-Agent Centralised Policy Gradients

schroederdewitt/multiagent_mujoco 14 Mar 2020

We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces.

Q-Learning SMAC +2

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?

Denys88/rl_games 18 Nov 2020

Most recently developed approaches to cooperative multi-agent reinforcement learning in the \emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function.

SMAC Starcraft

MAVEN: Multi-Agent Variational Exploration

Denys88/rl_games NeurIPS 2019

We specifically focus on QMIX [40], the current state-of-the-art in this domain.


UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers

hhhusiyi-monash/UPDeT 20 Jan 2021

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task.


SMIX($λ$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning

chaovven/SMIX 11 Nov 2019

Learning a stable and generalizable centralized value function (CVF) is a crucial but challenging task in multi-agent reinforcement learning (MARL), as it has to deal with the issue that the joint action space increases exponentially with the number of agents in such scenarios.

SMAC Starcraft

Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best

SimonLucas/ntbea 3 Jan 2019

This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation.