{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/appo","slug":"appo","name":"APPO","full_name":"Asynchronous Proximal Policy Optimization","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","paper":"/paper/sample-factory-egocentric-3d-control-from","first_author":"Aleksei Petrenko","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sample-factory-egocentric-3d-control-from"},"source":{"url":"https://arxiv.org/abs/2006.11751v2","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Distributed Reinforcement Learning","url":"/methods/category/distributed-reinforcement-learning","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/adversarial-policy-optimization-for-offline","slug":"adversarial-policy-optimization-for-offline","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05306","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oh-lab/APPO"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/stableprompt-automatic-prompt-tuning-using","slug":"stableprompt-automatic-prompt-tuning-using","title":"StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models","date":"2024-10-10","arxiv_id":"2410.07652","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["kmc0207/Stableprompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/rl-based-stateful-neural-adaptive-sampling","slug":"rl-based-stateful-neural-adaptive-sampling","title":"RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing","date":"2023-10-05","arxiv_id":"2310.03507","n_code_links":1,"syntology":null},{"paper":"/paper/sample-factory-egocentric-3d-control-from","slug":"sample-factory-egocentric-3d-control-from","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11751","n_code_links":4,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alex-petrenko/sample-factory"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":4,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/appo/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/appo/papers/ran/1","json":"/method/appo/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":2},{"task":"/task/continuous-control","name":"Continuous Control","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/fps-games","name":"FPS Games","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/general-reinforcement-learning","name":"General Reinforcement Learning","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/text-classification","name":"Text Classification","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1},{"task":"/task/continuous-control","name":"continuous-control","papers":1},{"task":"/task/text-classification-1","name":"text-classification","papers":1}],"tasks_shown":15,"n_tasks":15,"usage_by_year":[{"year":"2020","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/appo"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=APPO","read_at":"2026-10-05T00:52:31+00:00","query":"APPO","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"Adaptive Proximal Policy Optimization (APPO)","origin_arxiv_id":"2410.07652"},"resolution":"alias","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2006.11751","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"outranked","may_be_wrong_sense":false,"bearers_found":3,"served":{"arxiv_id":"2410.07652","citations":null},"leading_other_bearer":{"arxiv_id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","citations":1,"named_by":["title_prefix","acronym_expansion"],"bearer_name":"APPO: Agentic Procedural Policy Optimization","ask_with":"have('2606.12384')"},"n_other_bearers_listed":2,"note":"'APPO' is ALSO the name of the paper 'APPO: Agentic Procedural Policy Optimization' (arXiv:2606.12384, 1 citations), which is cited more than the paper this answer is about (citations not recorded). The margin is narrow, so this is not a claim that the other one is what you meant -- check `served.arxiv_id` against the paper you had in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2410.07652","page":"/paper/stableprompt-automatic-prompt-tuning-using","syntology_url":"https://syntology.ai/paper/2410.07652","in_graph_layer":true,"samples":9,"ran":5,"n_ran_checked":2,"n_instrument":3,"unverified":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"about another paper, arXiv:2410.07652: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Adaptive Proximal Policy Optimization (APPO)' (resolution: alias); this answer is about that name. About another paper: this answer is about arXiv:2410.07652, while the archive credits arXiv:2006.11751.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"a2ebb2596f0f83efe05d009d0a87187f8c36a72525215384fb060659accad829","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}