{"url":"/dataset/procgen","name":"ProcGen","full_name":null,"description_markdown":"Procgen Benchmark includes 16 simple-to-use procedurally-generated environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills.","description_withheld":null,"homepage":"https://openai.com/blog/procgen-benchmark/","introduced_date":"2019-12-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/leveraging-procedural-generation-to-benchmark","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","first_author":"Karl Cobbe","url":null},"license":null,"modalities":[],"tasks":[{"name":"General Reinforcement Learning","url":"/task/general-reinforcement-learning","datasets_with_task":"/datasets/task/general-reinforcement-learning"},{"name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1","datasets_with_task":"/datasets/task/reinforcement-learning-1"}],"languages":[],"variants":["ProcGen"],"data_loaders":[],"num_papers_in_archive":177,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/reinforcement-learning-on-procgen","task":"Reinforcement Learning (RL)","dataset_variant":"ProcGen","rows":2,"metrics":["Mean Normalized Performance"],"first_row_in_archive_order":{"model":"PPG","paper":"/paper/phasic-policy-gradient","metrics":{"Mean Normalized Performance":"0.757"},"code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/ppg.py"},{"title":"openai/phasic-policy-gradient","url":"https://github.com/openai/phasic-policy-gradient"},{"title":"jjccero/pbrl","url":"https://github.com/jjccero/pbrl/tree/master/pbrl/algorithms/ppg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/phasic-policy-gradient","title":"Phasic Policy Gradient","date":"2020-09-09","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":0,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":13,"samples_ran":0,"samples_unverified":13,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}