marl
Datasets
All datasets matching “marl”marl-gpt-datasets
MARL-GPT Datasets
Offline expert trajectories from “MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning”.
Environments
This dataset includes trajectories from the three evaluation domains used in MARL-GPT: SMACv2 (StarCraft multi-agent combat), Google Research Football (GRF), and POGEMA (partially observable multi-agent pathfinding on grids).
Format
Trajectories are stored sequentially (no shuffling). Use the done flag to split the stream into… See the full description on the dataset page: https://huggingface.co/datasets/nortem/marl-gpt-datasets.og-marl
@misc{formanek2024puttingdatacentreoffline,
title={Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning},
author={Claude Formanek and Louise Beyers and Callum Rhys Tilbury and Jonathan P. Shock and Arnu Pretorius},
year={2024},
eprint={2409.12001},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2409.12001},
}
marlin-assetsmarl_checkpointopenwebtext-gemma-2-context-128
OpenWebTextCorpus tokenized for Gemma 2 with 128 context size
This dataset is a pre-tokenized version of the Skylion007/openwebtext dataset
using the gemma tokenizer. As such, this dataset follows the same licensing as the original openwebtext dataset.
This pre-tokenization is done as a performance optimization for using the openwebtext dataset with a Gemma model (gemma-2b, gemma-2b-it, gemma-7b, gemma-7b-it).
This dataset was created using SAELens, with the following settings:… See the full description on the dataset page: https://huggingface.co/datasets/Marlon154/openwebtext-gemma-2-context-128.marlin