SMAC
38 papers with code • 11 benchmarks • 1 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.
Benchmarks
These leaderboards are used to track progress in SMAC
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find SMAC models and implementations
SMAC
Latest papers
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
In this work, we conduct new analysis demonstrating that SMAC lacks the stochasticity and partial observability to require complex *closed-loop* policies.
Effects of Spectral Normalization in Multi-agent Reinforcement Learning
kinalmehta/epymarl_spectral
•
•
A reliable critic is central to on-policy actor-critic learning.
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
opendilab/ace
•
•
In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.
Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition
liushunyu/cia
•
•
Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards, and has recently emerged as a powerful credit assignment paradigm for tackling cooperative Multi-Agent Reinforcement Learning (MARL) problems.
Latent State Marginalization as a Low-cost Approach for Improving Exploration
zdhnarsil/stochastic-marginal-actor-critic
•
•
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework -- often touted for its exploration and robustness capabilities -- is usually motivated from a probabilistic perspective, the use of deep probabilistic models has not gained much traction in practice due to their inherent complexity.
Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft
The StarCraft II Multi-Agent Challenge (SMAC) was created to be a challenging benchmark problem for cooperative multi-agent reinforcement learning (MARL).
Scalable Multi-Agent Model-Based Reinforcement Learning
While in mixed environments full autonomy of the agents can be a desirable outcome, cooperative environments allow agents to share information to facilitate coordination.
Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards.
Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks
reinholdm/offline-pre-trained-multi-agent-decision-transformer
•
•
In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL.
SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning
hsvgbkhgbv/shapley-q-learning
•
•
This paper studies a theoretical framework for value factorisation with interpretability via Shapley value theory.
