{"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":"/paper/winner-takes-it-all-training-performant-rl-1","title":"Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization","arxiv_id":"2210.03475","date":"2022-10-07","proceeding":"NeurIPS 2023 11","authors":["Nathan Grinsztajn","Daniel Furelos-Blanco","Shikha Surana","Clément Bonnet","Thomas D. Barrett"],"abstract":"Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic to expect an agent to solve these (often NP-)hard problems in a single shot at inference due to their inherent complexity. Thus, leading approaches often implement additional search strategies, from stochastic sampling and beam search to explicit fine-tuning. In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference. To this end, we introduce Poppy, a simple training procedure for populations. Instead of relying on a predefined or hand-crafted notion of diversity, Poppy induces an unsupervised specialization targeted solely at maximizing the performance of the population. We show that Poppy produces a set of complementary policies, and obtains state-of-the-art RL results on four popular NP-hard problems: traveling salesman, capacitated vehicle routing, 0-1 knapsack, and job-shop scheduling.","url_abs":"https://arxiv.org/abs/2210.03475v2","url_pdf":"https://arxiv.org/pdf/2210.03475v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"winner-takes-it-all-training-performant-rl-1","repo_url":"https://github.com/instadeepai/poppy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"job-shop-scheduling","task_name":"Job Shop Scheduling"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.03475","atlas_url":"https://app.syntology.ai/?focus=2210.03475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03475"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.03475"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.03475"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.03475\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2210.03475"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.03475\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.03475"},"call":"get_concepts_for_paper(arxiv_id=\"2210.03475\")"}],"by_repo":[{"repo":"instadeepai/poppy","kind":"listed","samples":8,"ran":5,"instrument":0,"unverified":3}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2210.03475.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2210.03475.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/instadeepai/poppy","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":3},"n_samples":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":8,"ran":5,"n_ran_checked":5,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"996e62c4cd6ed060","code_sha256_prefix":"996e62c4cd6ed060","entry":"get_acting_keys","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/data.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"act_key:ArrayImpl/1/int, num_start_positions:int/0/int, num_problems:int/0/int, num_agents:int/0/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-25T07:03:27.906132+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"996e62c4cd6ed060"}},{"code_sha256":"68f8056fb0caa770","code_sha256_prefix":"68f8056fb0caa770","entry":"get_agent_contributions","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/metrics.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"performance_matrix:ArrayImpl/2/float","fixture_out_type":"dict","level_recorded_at":"2026-09-25T07:03:27.906132+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"68f8056fb0caa770"}},{"code_sha256":"6f3252b61d4427b7","code_sha256_prefix":"6f3252b61d4427b7","entry":"get_optimizer","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/trainers/trainer.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/trainers/trainer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"cfg:DictConfig/0/?","fixture_out_type":"MultiSteps","level_recorded_at":"2026-09-25T07:03:27.906132+00:00","code_page":"/code/get-optimizer","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6f3252b61d4427b7"}},{"code_sha256":"fb96068e6f59c9ac","code_sha256_prefix":"fb96068e6f59c9ac","entry":"get_pop_performance_with_random_agents","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/metrics.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"performance_matrix:ArrayImpl/2/float, key:ArrayImpl/1/int","fixture_out_type":"dict","level_recorded_at":"2026-09-25T07:03:27.906132+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fb96068e6f59c9ac"}},{"code_sha256":"883057f04316e98e","code_sha256_prefix":"883057f04316e98e","entry":"get_start_positions","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/data.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"environment:MockEnvironment/0/?, start_key:ArrayImpl/1/int, num_start_positions:int/0/int, num_problems:int/0/int, num_agents:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T08:34:48.807261+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"883057f04316e98e"}},{"code_sha256":"05089f65276ed271","code_sha256_prefix":"05089f65276ed271","entry":"get_metrics","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/metrics.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-metrics","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05089f65276ed271"}},{"code_sha256":"a5bda23e4f88eecf","code_sha256_prefix":"a5bda23e4f88eecf","entry":"get_params","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/trainers/validation.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/trainers/validation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-params","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from instadeepai/compass, and GitHub could not classify the licence of that repository (NOASSERTION)","mcp_get_code":{"code_sha256":"a5bda23e4f88eecf"}},{"code_sha256":"5720de557f409693","code_sha256_prefix":"5720de557f409693","entry":"load_checkpoint","repo":"instadeepai/poppy","repo_kind":"listed","path":"poppy/utils/checkpoint.py","file_url":"https://github.com/instadeepai/poppy/blob/HEAD/poppy/utils/checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-checkpoint","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5720de557f409693"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4f1af737d06ad8e0f6293eab6f1c2c14340b8fc12654f8c46edf7e539eba7100","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}