{"url":"/dataset/spaceship-dataset","name":"Spaceship Dataset","full_name":null,"description_markdown":"The Spaceship dataset is a dataset for evaluating agents’ ability to learn to solve a class of physics-based tasks. The tasks consist on a spaceship that has to reach a the mothership in 11 steps, in an environment where static planets exert gravitational forces on the spaceship, which induce complex non-linear dynamics on the motion over the 11 steps.\n\nSource: [https://arxiv.org/pdf/1705.02670.pdf](https://arxiv.org/pdf/1705.02670.pdf)","description_withheld":null,"homepage":"https://github.com/deepmind/spaceship_dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/metacontrol-for-adaptive-imagination-based","title":"Metacontrol for Adaptive Imagination-Based Optimization","first_author":"Jessica B. Hamrick","url":null},"license":null,"modalities":[],"tasks":[{"name":"Decision Making","url":"/task/decision-making","datasets_with_task":"/datasets/task/decision-making"}],"languages":[],"variants":["Spaceship Dataset"],"data_loaders":[{"repo":"https://github.com/deepmind/spaceship_dataset","url":"https://github.com/deepmind/spaceship_dataset","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}