Learning Compositional Koopman Operators for Model-Based Control
Authors: Yunzhu Li, Hao He, Jiajun Wu, Dina Katabi, Antonio Torralba
ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments on manipulating ropes and controlling soft robots show that the proposed method has better efficiency and generalization ability than existing baselines.4 EXPERIMENTS |
| Researcher Affiliation | Academia | Yunzhu Li MIT CSAIL Hao He MIT CSAIL Jiajun Wu MIT CSAIL Dina Katabi MIT CSAIL Antonio Torralba MIT CSAIL |
| Pseudocode | No | The paper describes the methodology using prose and mathematical equations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our project page: http://koopman.csail.mit.edu |
| Open Datasets | No | We generate 10,000 episodes for Rope and 50,000 episodes for Soft and Swim. The paper describes generating its own datasets but does not provide any concrete access information (link, DOI, repository, or formal citation) to make them publicly available. |
| Dataset Splits | No | We generate 10,000 episodes for Rope and 50,000 episodes for Soft and Swim. Among them, 90% are used for training, and the rest for testing. The paper specifies training and testing splits, but does not explicitly mention a separate validation dataset split. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Adam optimizer (Kingma & Ba, 2015)' but does not provide specific software dependencies with version numbers (e.g., Python, PyTorch/TensorFlow, CUDA versions). |
| Experiment Setup | Yes | All models are trained using Adam optimizer (Kingma & Ba, 2015) with a learning rate of 10 4 and a batch size of 8. λ1 and λ2 are 1.0 and 0.3, respectively, for our model. For both our model and the baselines, we apply 400K iterations of gradient steps in the Rope environment and 580K iterations in the Soft and Swim environment. |