{"url":"/dataset/seaquest-openai-gym","name":"Seaquest - OpenAI Gym","full_name":"Seaquest - OpenAI Gym","description_markdown":"Dataset: The experiments are conducted using the Seaquest environment from the OpenAI Gym framework, which simulates the Atari 2600 game Seaquest. The dataset consists of RGB frames (210x160x3) generated dynamically during training. These frames are preprocessed by converting to grayscale, resizing to 84x84 pixels, and stacking four consecutive frames to form a 4x84x84 tensor, capturing temporal dynamics of the game state. No external or pre-collected dataset is used; the data is produced through real-time interaction with the Gym environment.","description_withheld":null,"homepage":"","introduced_date":"2012-07-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-arcade-learning-environment-an-evaluation","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","first_author":"Marc G. Bellemare","url":null},"license":null,"modalities":[],"tasks":[{"name":"Reinforcement Learning (Atari Games)","url":"/task/reinforcement-learning-atari-games","datasets_with_task":"/datasets/task/reinforcement-learning-atari-games"}],"languages":[],"variants":["Seaquest - OpenAI Gym"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/reinforcement-learning-atari-games-on","task":"Reinforcement Learning (Atari Games)","dataset_variant":"Seaquest - OpenAI Gym","rows":1,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"BanditDQN","paper":"/paper/adaptive-action-duration-with-contextual","metrics":{"Average Return":"87 ± 45"},"code_links":[{"title":"abhi460729/Action-Duration-with-Contextual-Bandits-for-Deep-Reinforcement-Learning-in-Dynamic-Environments","url":"https://github.com/abhi460729/Action-Duration-with-Contextual-Bandits-for-Deep-Reinforcement-Learning-in-Dynamic-Environments"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/adaptive-action-duration-with-contextual","title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments","date":"2025-06-17","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}