{"url":"/sota/mujoco-games-on-walker2d","task":{"name":"MuJoCo Games","url":"/task/mujoco-games","note":null},"dataset":{"name":"Walker2d","url":null},"category":"Robots","categories":["Robots"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Mean"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean":null}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"IQ-Learn","metrics":{"Mean":"5134"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/iq-learn-inverse-soft-q-learning-for","paper_url":"https://arxiv.org/abs/2106.12142v4","paper_title":"IQ-Learn: Inverse soft-Q Learning for Imitation","code":"https://github.com/Div99/IQ-Learn","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"POP3D","metrics":{"Mean":"3966.01"},"uses_additional_data":false,"paper_date":"2018-07-02","paper":"/paper/policy-optimization-with-penalized-point","paper_url":"http://arxiv.org/abs/1807.00442v4","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","code":"https://github.com/cxxgtxy/POP3D","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}