Starcraft

126 papers with code • 0 benchmarks • 6 datasets

Starcraft I is a RTS game; the task is to train an agent to play the game.

( Image credit: Macro Action Selection with Deep Reinforcement Learning in StarCraft )

Libraries

Use these libraries to find Starcraft models and implementations
4 papers
10
3 papers
1,701
3 papers
34
See all 10 libraries.

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning

colazhang22/pps-qmix 5 Mar 2024

Agents share Q-value network periodically during the training process.

2
05 Mar 2024

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

hyunghona/emu 2 Mar 2024

To address this, we introduce Efficient episodic Memory Utilization (EMU) for MARL, with two primary objectives: (a) accelerating reinforcement learning by leveraging semantically coherent memory from an episodic buffer and (b) selectively promoting desirable transitions to prevent local convergence.

10
02 Mar 2024

SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models

ramsayxiaoshao/SwarmBrain-Embodied-agent-for-real-time-strategy-game-StarCraft-II-via-large-language-models 31 Jan 2024

In this paper, we introduce SwarmBrain, an embodied agent leveraging LLM for real-time strategy implementation in the StarCraft II game environment.

1
31 Jan 2024

Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach

histmeisah/large-language-models-play-starcraftii 19 Dec 2023

StarCraft II is a challenging benchmark for AI agents due to the necessity of both precise micro level operations and strategic macro awareness.

141
19 Dec 2023

CODEX: A Cluster-Based Method for Explainable Reinforcement Learning

ainfosec/codex 7 Dec 2023

Despite the impressive feats demonstrated by Reinforcement Learning (RL), these algorithms have seen little adoption in high-risk, real-world applications due to current difficulties in explaining RL agent actions and building user trust.

0
07 Dec 2023

JaxMARL: Multi-Agent RL Environments in JAX

flairox/jaxmarl 16 Nov 2023

This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL.

304
16 Nov 2023

FoX: Formation-aware exploration in multi-agent reinforcement learning

hyeon1996/fox 22 Aug 2023

Recently, deep multi-agent reinforcement learning (MARL) has gained significant popularity due to its success in various cooperative multi-agent tasks.

1
22 Aug 2023

AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning

deepmind/alphastar 7 Aug 2023

StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires strategic planning over long time horizons with real-time low-level execution.

333
07 Aug 2023

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

zhengyinan-air/omiga NeurIPS 2023

Offline reinforcement learning (RL) has received considerable attention in recent years due to its attractive capability of learning policies from offline datasets without environmental interactions.

21
21 Jul 2023

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

pku-marl/harl 19 Jun 2023

We embed cooperative MARL problems into probabilistic graphical models, from which we derive the maximum entropy (MaxEnt) objective for MARL.

316
19 Jun 2023