Starcraft II
81 papers with code • 3 benchmarks • 4 datasets
Starcraft II is a RTS game; the task is to train an agent to play the game.
( Image credit: The StarCraft Multi-Agent Challenge )
Benchmarks
These leaderboards are used to track progress in Starcraft II
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Starcraft II models and implementations
StarCraft II Learning Environment
SMAC-Exp
Lani
MSC
Latest papers
Semantic HELM: A Human-Readable Memory for Reinforcement Learning
Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement Learning
ZYC9894/EXPODE-master
•
•
International Conference on Autonomous Agents and Multiagent Systems 2023
Recently, Multi-Agent Reinforcement Learning (MARL) has been applied to a large number of scenarios and has shown promising performance.
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
zyh1999/cadp
•
•
Despite the encouraging results achieved, CTDE makes an independence assumption on agent policies, which limits agents to adopt global cooperative information from each other during centralized training.
SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
The Starcraft Multi-Agent Challenge (SMAC) has been widely used in MARL research, but is built on top of a heavy, closed-source computer game, StarCraft II.
Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles
Role-based learning is a promising approach to improving the performance of Multi-Agent Reinforcement Learning (MARL).
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
dig-beihang/ami
•
•
To achieve maximum deviation in victim policies under complex agent-wise interactions, our unilateral attack aims to characterize and maximize the impact of the adversary on the victims.
TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems
Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL).
Self-Motivated Multi-Agent Exploration
In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration.
Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient
Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces.
On Efficient Reinforcement Learning for Full-length Game of StarCraft II
In this work, we investigate a set of RL techniques for the full-length game of StarCraft II.
