{"url":"/task/atari-games-100k","name":"Atari Games 100k","slug":"atari-games-100k","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":18,"papers_with_code":16,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/atari-100k","name":"Atari 100k","full_name":"","num_papers_in_archive":62}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":16,"of":16,"tagged_in_all":18,"items":[{"url":"/paper/mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","arxiv_id":"1911.08265","repositories_listed":18,"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}},{"url":"/paper/mastering-diverse-domains-through-world","title":"Mastering Diverse Domains through World Models","date":"2023-01-10","arxiv_id":"2301.04104","repositories_listed":7,"syntology":{"n":34,"n_ran":21,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/curl-contrastive-unsupervised-representations","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","date":"2020-04-08","arxiv_id":"2004.04136","repositories_listed":7,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","date":"2020-04-28","arxiv_id":"2004.13649","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/bigger-better-faster-human-level-atari-with","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","date":"2023-05-30","arxiv_id":"2305.19452","repositories_listed":3,"syntology":null},{"url":"/paper/mastering-atari-games-with-limited-data","title":"Mastering Atari Games with Limited Data","date":"2021-10-30","arxiv_id":"2111.00210","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/transformers-are-sample-efficient-world","title":"Transformers are Sample-Efficient World Models","date":"2022-09-01","arxiv_id":"2209.00588","repositories_listed":2,"syntology":{"n":26,"n_ran":17,"n_unverified":9,"n_pointer_only":26}},{"url":"/paper/model-based-reinforcement-learning-for-atari","title":"Model-Based Reinforcement Learning for Atari","date":"2019-03-01","arxiv_id":"1903.00374","repositories_listed":2,"syntology":{"n":21,"n_ran":15,"n_unverified":6,"n_pointer_only":17}},{"url":"/paper/storm-efficient-stochastic-transformer-based-1","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","date":"2023-10-14","arxiv_id":"2310.09615","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","arxiv_id":"2310.00344","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/on-the-feasibility-of-cross-task-transfer","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","date":"2022-10-19","arxiv_id":"2210.10763","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/pretraining-the-vision-transformer-using-self","title":"Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning","date":"2022-09-22","arxiv_id":"2209.10901","repositories_listed":1,"syntology":null},{"url":"/paper/the-primacy-bias-in-deep-reinforcement","title":"The Primacy Bias in Deep Reinforcement Learning","date":"2022-05-16","arxiv_id":"2205.07802","repositories_listed":1,"syntology":null},{"url":"/paper/pretraining-representations-for-data","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04799","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/data-efficient-reinforcement-learning-with-1","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","date":"2020-07-12","arxiv_id":"2007.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}