{"about":{"site":"https://codewithpapers.app","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.","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"},"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"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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},"by_repo_kind":{"listed":{"samples":8,"ran":5,"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":0,"samples":[{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"996e62c4cd6ed060"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68f8056fb0caa770"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f3252b61d4427b7"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb96068e6f59c9ac"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"883057f04316e98e"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05089f65276ed271"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5bda23e4f88eecf"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5720de557f409693"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}