{"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/promp-proximal-meta-policy-search","title":"ProMP: Proximal Meta-Policy Search","arxiv_id":"1810.06784","date":"2018-10-16","proceeding":"ICLR 2019 5","authors":["Jonas Rothfuss","Dennis Lee","Ignasi Clavera","Tamim Asfour","Pieter Abbeel"],"abstract":"Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provides a theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights we develop a novel meta-learning algorithm that overcomes both the issue of poor credit assignment and previous difficulties in estimating meta-policy gradients. By controlling the statistical distance of both pre-adaptation and adapted policies during meta-policy search, the proposed algorithm endows efficient and stable meta-learning. Our approach leads to superior pre-adaptation policy behavior and consistently outperforms previous Meta-RL algorithms in sample-efficiency, wall-clock time, and asymptotic performance.","url_abs":"https://arxiv.org/abs/1810.06784v4","url_pdf":"https://arxiv.org/pdf/1810.06784v4.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":"promp-proximal-meta-policy-search","repo_url":"https://github.com/jonasrothfuss/promp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"promp-proximal-meta-policy-search","repo_url":"https://github.com/Zhiwei-Z/PrompLimitTest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"promp-proximal-meta-policy-search","repo_url":"https://github.com/Zhiwei-Z/SeqPromp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"promp-proximal-meta-policy-search","repo_url":"https://github.com/Zhiwei-Z/prompzzw","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"promp-proximal-meta-policy-search","repo_url":"https://github.com/clrrrr/promp_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"promp-proximal-meta-policy-search","repo_url":"https://github.com/learnables/learn2learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.06784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.06784"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/jonasrothfuss/promp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zhiwei-Z/PrompLimitTest","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/learnables/learn2learn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clrrrr/promp_plus","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zhiwei-Z/prompzzw","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zhiwei-Z/SeqPromp","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":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":0,"samples":[{"code_sha256_prefix":"d1746c5f80182931","entry":"encode_args","repo":"jonasrothfuss/promp","repo_kind":"official","path":"experiment_utils/experiment.py","file_url":"https://github.com/jonasrothfuss/promp/blob/HEAD/experiment_utils/experiment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1746c5f80182931"}},{"code_sha256_prefix":"bb1c1cc1a07047fc","entry":"get_args","repo":"jonasrothfuss/promp","repo_kind":"official","path":"experiment_utils/experiment.py","file_url":"https://github.com/jonasrothfuss/promp/blob/HEAD/experiment_utils/experiment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb1c1cc1a07047fc"}},{"code_sha256_prefix":"a384fd2f6407795c","entry":"magic_box","repo":"jonasrothfuss/promp","repo_kind":"official","path":"meta_policy_search/meta_algos/dice_maml.py","file_url":"https://github.com/jonasrothfuss/promp/blob/HEAD/meta_policy_search/meta_algos/dice_maml.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a384fd2f6407795c"}},{"code_sha256_prefix":"2ecadc377950bf7b","entry":"query_yes_no","repo":"jonasrothfuss/promp","repo_kind":"official","path":"experiment_utils/utils.py","file_url":"https://github.com/jonasrothfuss/promp/blob/HEAD/experiment_utils/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ecadc377950bf7b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}