{"url":"/dataset/alchemy","name":"Alchemy","full_name":null,"description_markdown":"The DeepMind Alchemy environment is a meta-reinforcement learning benchmark that presents tasks sampled from a task distribution with deep underlying structure. It was created to test for the ability of agents to reason and plan via latent state inference, as well as useful exploration and experimentation. \r\n\r\nAlchemy is a single-player video game, implemented in Unity. The player sees a first-person view of a table with a number of objects on it, including a set of colored stones, a set of dishes containing colored potions, and a central cauldron. Stones have different point values, and points are collected when stones are added to the cauldron. By dipping stones into the potions, the player can transform the stones’ appearance, and thus their value, increasing the number of points that can be won.\r\n\r\nSource: [dm_alchemy: DeepMind Alchemy environment](https://github.com/deepmind/dm_alchemy)\r\n\r\nImage Source: [dm_alchemy: DeepMind Alchemy environment](https://github.com/deepmind/dm_alchemy)","description_withheld":null,"homepage":"https://github.com/deepmind/dm_alchemy","introduced_date":"2021-02-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/alchemy-a-structured-task-distribution-for","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","first_author":"Jane X. Wang","url":null},"license":null,"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[],"languages":[],"variants":["Alchemy"],"data_loaders":[{"repo":"https://github.com/deepmind/dm_alchemy","url":"https://github.com/deepmind/dm_alchemy","frameworks":[]}],"num_papers_in_archive":4,"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."}