{"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/mdpo","slug":"mdpo","name":"MDPO","full_name":"Mirror Descent Policy Optimization","full_name_withheld":false,"description_markdown":"**Mirror Descent Policy Optimization (MDPO)** is a policy gradient algorithm based on the idea of iteratively solving a trust-region problem that minimizes a sum of two terms: a linearization of the standard RL objective function and a proximity term that restricts two consecutive updates to be close to each other. It is based on Mirror Descent, which is a general trust region method that\r\nattempts to keep consecutive iterates close to each other.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Mirror Descent Policy Optimization","paper":"/paper/mirror-descent-policy-optimization","first_author":"Manan Tomar","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mirror-descent-policy-optimization"},"source":{"url":"https://arxiv.org/abs/2005.09814v5","title":"Mirror Descent Policy Optimization","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":"Policy Gradient Methods","url":"/methods/category/policy-gradient-methods","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":null,"slug":"fast-convergence-of-softmax-policy-mirror","title":"Fast Convergence of Softmax Policy Mirror Ascent","date":"2024-11-18","arxiv_id":"2411.12042","n_code_links":0,"syntology":null},{"paper":"/paper/mdpo-conditional-preference-optimization-for","slug":"mdpo-conditional-preference-optimization-for","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11839","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":2,"n_instrument":3,"unverified":5,"pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["luka-group/mDPO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"model-based-decentralized-policy-optimization","title":"Model-Based Decentralized Policy Optimization","date":"2023-02-16","arxiv_id":"2302.08139","n_code_links":0,"syntology":null},{"paper":"/paper/mirror-descent-policy-optimization","slug":"mirror-descent-policy-optimization","title":"Mirror Descent Policy Optimization","date":"2020-05-20","arxiv_id":"2005.09814","n_code_links":1,"syntology":null}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":2,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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":1,"papers_where_code_ran_first_page":"/method/mdpo/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/mdpo/papers/ran/1","json":"/method/mdpo/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/continuous-control","name":"Continuous Control","papers":1},{"task":"/task/hallucination","name":"Hallucination","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/mujoco","name":"MuJoCo","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/continuous-control","name":"continuous-control","papers":1},{"task":"/task/model","name":"model","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":1},{"year":"2023","papers":1},{"year":"2024","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/mdpo"},"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=MDPO","read_at":"2026-10-05T00:59:01+00:00","query":"MDPO","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":"MDPO","origin_arxiv_id":"2406.11839"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2005.09814","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":5,"served":{"arxiv_id":"2406.11839","citations":95},"leading_other_bearer":{"arxiv_id":"2508.13148","title":"MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models","citations":30,"named_by":["title_prefix"],"bearer_name":"MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models","ask_with":"have('2508.13148')"},"n_other_bearers_listed":4,"note":"4 other thing(s) here are also called 'MDPO', 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":"2406.11839","page":"/paper/mdpo-conditional-preference-optimization-for","syntology_url":"https://syntology.ai/paper/2406.11839","in_graph_layer":true,"samples":10,"ran":5,"n_ran_checked":2,"n_instrument":3,"unverified":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"about another paper, arXiv:2406.11839: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). About another paper: this answer is about arXiv:2406.11839, while the archive credits arXiv:2005.09814.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"f27d31266112de23ef206771a8650b8dcba829d1a49cfa6798a5283b6aec104c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}