{"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,"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","title":"SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem","date":"2025-05-28","arxiv_id":"2505.21887","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}},{"paper":"/paper/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","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","date":"2023-06-29","arxiv_id":"2306.17100","n_code_links":3,"syntology":{"ran":0,"of":16,"unverified":16,"pointer_only":3}},{"paper":"/paper/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,"unverified":1,"pointer_only":3}},{"paper":"/paper/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,"unverified":7,"pointer_only":8}}],"papers_shown":6,"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":"2026-09-24T18:15:14+00:00"}