ml-jku/dm_control

--- license: mit task_categories: - reinforcement-learning --- # DMControl 1M This repository contains the [DMControl](https://arxiv.org/abs/1801.00690) datasets as used in [Learning to Modulate Pre-trained Models in RL](https://arxiv.org/abs/2306.14884): - Trajectories for every task are stored as separate `.npz` files. - Every `.npz` file contains 1M transitions. Download the dataset using the `huggingface-cli`: ``` huggingface-cli download ml-jku/dm_control --local-dir=./dm_control --repo-type dataset ``` For dataloading we refer to our Github repository: https://github.com/ml-jku/L2M Citation: ``` @article{schmied2024learning, title={Learning to Modulate pre-trained Models in RL}, author={Schmied, Thomas and Hofmarcher, Markus and Paischer, Fabian and Pascanu, Razvan and Hochreiter, Sepp}, journal={Advances in Neural Information Processing Systems}, volume={36}, year={2024} } ```--- 许可证：MIT许可证 任务类别： - 强化学习 --- # DMControl 1M 本仓库包含了[DMControl](https://arxiv.org/abs/1801.00690)数据集，该数据集为论文《强化学习中预训练模型的调制学习》（https://arxiv.org/abs/2306.14884）所使用： - 每个任务的轨迹均存储为独立的`.npz`文件。 - 每个`.npz`文件包含100万条转移样本。 可通过`huggingface-cli`工具下载该数据集： huggingface-cli download ml-jku/dm_control --local-dir=./dm_control --repo-type dataset 关于数据加载的相关实现，请参考我们的GitHub仓库：https://github.com/ml-jku/L2M 引用格式： @article{schmied2024learning, title={强化学习中预训练模型的调制学习}, author={Schmied, Thomas and Hofmarcher, Markus and Paischer, Fabian and Pascanu, Razvan and Hochreiter, Sepp}, journal={《神经信息处理系统进展》}, volume={36}, year={2024} }