EMU

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

(★ 57)

(Official) PyTorch implementation for Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (EMU) (ICLR 2024, Oral)

EMU Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# EMU: Efficient Episodic Memory Utilization of Cooperative Multi-agent Reinforcement Learning

# Note
This codebase accompanies the paper submission "**Efficient Episodic Memory Utilization of Cooperative Multi-agent Reinforcement Learning (EMU)**" and is based on [GRF](https://github.com/google-research/football), [PyMARL](https://github.com/oxwhirl/pymarl) and [SMAC](https://github.com/oxwhirl/smac) which are open-sourced.
The paper is accepted by [ICLR2024](https://iclr.cc/Conferences/2024/) and now available in [OpenReview](https://openreview.net/forum?id=LjivA1SLZ6) and [arXiv](https://arxiv.org/abs/2403.01112).

PyMARL is [WhiRL](http://whirl.cs.ox.ac.uk)'s framework for deep multi-agent reinforcement learning and our code includes implementations of the following algorithms:
- [**QPLEX**: Duplex Dueling Multi-Agent Q-Learning](https://arxiv.org/pdf/2008.01062)
- [**EMC**: Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration](https://arxiv.org/abs/2111.11032)
- [**CDS**: Celebrating Diversity in Shared Multi-Agent Reinforcement Learning](https://arxiv.org/abs/2106.02195)

# Run an experiment

**Note: Please use the updated configuration file for experiments. We have corrected some errors in the previously uploaded configurations.**
To train EMU(QPLEX) on SC2 setting tasks, run the following command:
```
python3 src/main.py --config=EMU_sc2 --env-config=sc2 with env_args.map_name=5m_vs_6m
```
For EMU(CDS), please change config file to EMU_sc2_cds.

To train EMU(QPLEX) on SC2 setting tasks, run the following command:
```
python3 src/main.py --config=EMU_grf --env-config=academy_3_vs_1_with_keeper
```
For EMU(CDS), please change config file to EMU_grf_cds.

# Publication
If you find this repository useful, please cite our paper:
```
@inproceedings{na2024efficient,
  title={Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning},
  author={Na, Hyungho and Seo, Yunkyeong and Moon, Il-chul},
  journal={arXiv preprint arXiv:2403.01112},
  year={2024}
}
```

EMU

EMU Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

EMU

EMU Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README