{"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/cem-rl-combining-evolutionary-and-gradient-1","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","arxiv_id":"1810.01222","date":"2018-10-02","proceeding":null,"authors":["Aloïs Pourchot","Olivier Sigaud"],"abstract":"Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are\ntwo popular approaches to policy search. The former is widely applicable and\nrather stable, but suffers from low sample efficiency. By contrast, the latter\nis more sample efficient, but the most sample efficient variants are also\nrather unstable and highly sensitive to hyper-parameter setting. So far, these\nfamilies of methods have mostly been compared as competing tools. However, an\nemerging approach consists in combining them so as to get the best of both\nworlds. Two previously existing combinations use either an ad hoc evolutionary\nalgorithm or a goal exploration process together with the Deep Deterministic\nPolicy Gradient (DDPG) algorithm, a sample efficient off-policy deep RL\nalgorithm. In this paper, we propose a different combination scheme using the\nsimple cross-entropy method (CEM) and Twin Delayed Deep Deterministic policy\ngradient (td3), another off-policy deep RL algorithm which improves over ddpg.\nWe evaluate the resulting method, cem-rl, on a set of benchmarks classically\nused in deep RL. We show that cem-rl benefits from several advantages over its\ncompetitors and offers a satisfactory trade-off between performance and sample\nefficiency.","url_abs":"http://arxiv.org/abs/1810.01222v3","url_pdf":"http://arxiv.org/pdf/1810.01222v3.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":"cem-rl-combining-evolutionary-and-gradient-1","repo_url":"https://github.com/apourchot/CEM-RL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cem-rl-combining-evolutionary-and-gradient-1","repo_url":"https://github.com/apourchot/EvoLearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.01222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.01222"}},"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/apourchot/CEM-RL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/apourchot/EvoLearn","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"a3d26709949c0939","entry":"evaluate","repo":"apourchot/CEM-RL","repo_kind":"official","path":"es_grad.py","file_url":"https://github.com/apourchot/CEM-RL/blob/HEAD/es_grad.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3d26709949c0939"}},{"code_sha256_prefix":"c53cbfe5f3c8aa9d","entry":"evaluate","repo":"apourchot/CEM-RL","repo_kind":"official","path":"distributed.py","file_url":"https://github.com/apourchot/CEM-RL/blob/HEAD/distributed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c53cbfe5f3c8aa9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}