{"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/evolved-policy-gradients","title":"Evolved Policy Gradients","arxiv_id":"1802.04821","date":"2018-02-13","proceeding":"NeurIPS 2018 12","authors":["Rein Houthooft","Richard Y. Chen","Phillip Isola","Bradly C. Stadie","Filip Wolski","Jonathan Ho","Pieter Abbeel"],"abstract":"We propose a metalearning approach for learning gradient-based reinforcement\nlearning (RL) algorithms. The idea is to evolve a differentiable loss function,\nsuch that an agent, which optimizes its policy to minimize this loss, will\nachieve high rewards. The loss is parametrized via temporal convolutions over\nthe agent's experience. Because this loss is highly flexible in its ability to\ntake into account the agent's history, it enables fast task learning. Empirical\nresults show that our evolved policy gradient algorithm (EPG) achieves faster\nlearning on several randomized environments compared to an off-the-shelf policy\ngradient method. We also demonstrate that EPG's learned loss can generalize to\nout-of-distribution test time tasks, and exhibits qualitatively different\nbehavior from other popular metalearning algorithms.","url_abs":"http://arxiv.org/abs/1802.04821v2","url_pdf":"http://arxiv.org/pdf/1802.04821v2.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":"evolved-policy-gradients","repo_url":"https://github.com/openai/EPG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"evolved-policy-gradients","repo_url":"https://github.com/victcebesp/Booster-Evolved-Policy-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"evolved-policy-gradients","repo_url":"https://github.com/victcebesp/EPGVariation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04821"}},"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/victcebesp/Booster-Evolved-Policy-Gradient","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openai/EPG","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/victcebesp/EPGVariation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"20922c79a0929bbf","entry":"flatten","repo":"victcebesp/Booster-Evolved-Policy-Gradient","repo_kind":"listed","path":"epg/viskit/core.py","file_url":"https://github.com/victcebesp/Booster-Evolved-Policy-Gradient/blob/HEAD/epg/viskit/core.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"20922c79a0929bbf"}},{"code_sha256_prefix":"40f81b1d5f51ea76","entry":"sliding_mean","repo":"openai/EPG","repo_kind":"official","path":"epg/viskit/frontend.py","file_url":"https://github.com/openai/EPG/blob/HEAD/epg/viskit/frontend.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40f81b1d5f51ea76"}},{"code_sha256_prefix":"6c7a4a9349a395e9","entry":"unique","repo":"openai/EPG","repo_kind":"official","path":"epg/viskit/frontend.py","file_url":"https://github.com/openai/EPG/blob/HEAD/epg/viskit/frontend.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c7a4a9349a395e9"}},{"code_sha256_prefix":"22ce513fe6d2b13e","entry":"gamma_expand","repo":"victcebesp/Booster-Evolved-Policy-Gradient","repo_kind":"listed","path":"epg/utils.py","file_url":"https://github.com/victcebesp/Booster-Evolved-Policy-Gradient/blob/HEAD/epg/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":false,"mcp_get_code":{"code_sha256":"22ce513fe6d2b13e"}},{"code_sha256_prefix":"b16faabc1615be78","entry":"get_dims","repo":"victcebesp/Booster-Evolved-Policy-Gradient","repo_kind":"listed","path":"epg/utils.py","file_url":"https://github.com/victcebesp/Booster-Evolved-Policy-Gradient/blob/HEAD/epg/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":false,"mcp_get_code":{"code_sha256":"b16faabc1615be78"}},{"code_sha256_prefix":"462821d355e6e526","entry":"load_progress","repo":"victcebesp/Booster-Evolved-Policy-Gradient","repo_kind":"listed","path":"epg/viskit/core.py","file_url":"https://github.com/victcebesp/Booster-Evolved-Policy-Gradient/blob/HEAD/epg/viskit/core.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":false,"mcp_get_code":{"code_sha256":"462821d355e6e526"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}