{"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/pomo","slug":"pomo","name":"POMO","full_name":"POMO","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","paper":"/paper/pomo-policy-optimization-with-multiple-optima","first_author":"Yeong-Dae Kwon","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pomo-policy-optimization-with-multiple-optima"},"source":{"url":"https://arxiv.org/abs/2010.16011v3","title":"POMO: Policy Optimization with Multiple Optima for 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":"Reinforcement Learning Frameworks","url":"/methods/category/reinforcement-learning-frameworks","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"slug":"synergizing-reinforcement-learning-and","title":"Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization","date":"2025-06-11","arxiv_id":"2506.09404","n_code_links":0,"syntology":null},{"paper":"/paper/svrpbench-a-realistic-benchmark-for","slug":"svrpbench-a-realistic-benchmark-for","title":"SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem","date":"2025-05-28","arxiv_id":"2505.21887","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yehias21/vrp-benchmarks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/too-big-so-fail-enabling-neural-construction","slug":"too-big-so-fail-enabling-neural-construction","title":"Too Big, so Fail? -- Enabling Neural Construction Methods to Solve Large-Scale Routing Problems","date":"2023-09-29","arxiv_id":"2309.17089","n_code_links":1,"syntology":null},{"paper":"/paper/rl4co-an-extensive-reinforcement-learning-for","slug":"rl4co-an-extensive-reinforcement-learning-for","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","date":"2023-06-29","arxiv_id":"2306.17100","n_code_links":3,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ai4co/rl4co","pytorch/rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/learning-to-solve-routing-problems-via","slug":"learning-to-solve-routing-problems-via","title":"Learning to Solve Routing Problems via Distributionally Robust Optimization","date":"2022-02-15","arxiv_id":"2202.07241","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jiang-yuan/Learning-routing-DRO"],"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":["found_in_text"]}}},{"paper":"/paper/pomo-policy-optimization-with-multiple-optima","slug":"pomo-policy-optimization-with-multiple-optima","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","date":"2020-10-30","arxiv_id":"2010.16011","n_code_links":3,"syntology":{"ran":1,"of":8,"n_ran_checked":1,"n_instrument":0,"unverified":7,"pointer_only":8,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["yd-kwon/POMO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":6,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":6,"with_a_code_link":5,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"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":4,"papers_where_code_ran_first_page":"/method/pomo/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/pomo/papers/ran/1","json":"/method/pomo/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/combinatorial-optimization","name":"Combinatorial Optimization","papers":4},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":3},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":3},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/evolutionary-algorithms","name":"Evolutionary Algorithms","papers":1},{"task":"/task/management","name":"Management","papers":1},{"task":"/task/navigate","name":"Navigate","papers":1},{"task":"/task/traveling-salesman-problem","name":"Traveling Salesman Problem","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":2},{"year":"2025","papers":2}],"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/pomo"},"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=POMO","read_at":"2026-10-05T01:00:31+00:00","query":"POMO","kind":"method","have":"verified_code","tier":null,"verified_implementation":true,"level":3,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"POMO","origin_arxiv_id":"2010.16011"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2010.16011","repositories":{"listed":null,"in_graph":3,"list_truncated":null,"strongest_link":null},"retrieve_with":"get_reference_implementation(name='POMO')","name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":2,"served":{"arxiv_id":"2010.16011","citations":693},"leading_other_bearer":{"arxiv_id":"1904.03111","title":"PoMo: Generating Entity-Specific Post-Modifiers in Context","citations":11,"named_by":["title_prefix"],"bearer_name":"PoMo: Generating Entity-Specific Post-Modifiers in Context","ask_with":"have('1904.03111')"},"n_other_bearers_listed":1,"note":"1 other thing(s) here are also called 'POMO', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2010.16011","page":"/paper/pomo-policy-optimization-with-multiple-optima","syntology_url":"https://syntology.ai/paper/2010.16011","in_graph_layer":true,"samples":8,"ran":1,"n_ran_checked":1,"n_instrument":0,"unverified":7,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"verified reference implementation at level V3. This answer is about arXiv:2010.16011, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"5b89eeba56aa5deb7ac08e61ee98d23cc7381b27036fd6540578fc7b245a5b0a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}