{"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/simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","arxiv_id":"1803.07055","date":"2018-03-19","proceeding":null,"authors":["Horia Mania","Aurelia Guy","Benjamin Recht"],"abstract":"A common belief in model-free reinforcement learning is that methods based on\nrandom search in the parameter space of policies exhibit significantly worse\nsample complexity than those that explore the space of actions. We dispel such\nbeliefs by introducing a random search method for training static, linear\npolicies for continuous control problems, matching state-of-the-art sample\nefficiency on the benchmark MuJoCo locomotion tasks. Our method also finds a\nnearly optimal controller for a challenging instance of the Linear Quadratic\nRegulator, a classical problem in control theory, when the dynamics are not\nknown. Computationally, our random search algorithm is at least 15 times more\nefficient than the fastest competing model-free methods on these benchmarks. We\ntake advantage of this computational efficiency to evaluate the performance of\nour method over hundreds of random seeds and many different hyperparameter\nconfigurations for each benchmark task. Our simulations highlight a high\nvariability in performance in these benchmark tasks, suggesting that commonly\nused estimations of sample efficiency do not adequately evaluate the\nperformance of RL algorithms.","url_abs":"http://arxiv.org/abs/1803.07055v1","url_pdf":"http://arxiv.org/pdf/1803.07055v1.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":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/modestyachts/ARS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/AnshMittal1811/AugmentedRandomSearch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/HardikJ7321/AugmentedRandomSearch-AI-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/Ji4chenLi/ARS_experiment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/MagaliDrumare/Augmented-Random-Search-ARS-Intuition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/alexis-jacq/numpy_ARS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/billchan226/poar-srl-4-robot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/cpow-89/Augmented-Random-Search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/data-science-in-mechanical-engineering/hci-gibo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/eric-erki/robotics-rl-srl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/google/evojax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/in1t3r/ARS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/jainpankul/Augmented-Random-Search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/kalifou/robotics-rl-srl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/kayuksel/pytorch-ars","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/nnaisense/pgpelib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/octothrope/ARS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/qihongl/demo-random-search-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/raja17021998/Augmented-Random-Search-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/sarmueller/gibo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/sbodenstein/Tutorials","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/suvhradipghosh07/Augmented-Random-Search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/tmjeong1103/RL_with_RAY","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"simple-random-search-provides-a-competitive","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.07055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07055"}},"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/sarmueller/gibo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jainpankul/Augmented-Random-Search","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/raja17021998/Augmented-Random-Search-Implementation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/billchan226/poar-srl-4-robot","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kayuksel/pytorch-ars","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tmjeong1103/RL_with_RAY","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexis-jacq/numpy_ARS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/data-science-in-mechanical-engineering/hci-gibo","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MagaliDrumare/Augmented-Random-Search-ARS-Intuition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nnaisense/pgpelib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HardikJ7321/AugmentedRandomSearch-AI-","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eric-erki/robotics-rl-srl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/modestyachts/ARS","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qihongl/demo-random-search-RL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/evojax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/suvhradipghosh07/Augmented-Random-Search","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ji4chenLi/ARS_experiment","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/in1t3r/ARS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sbodenstein/Tutorials","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/octothrope/ARS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kalifou/robotics-rl-srl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cpow-89/Augmented-Random-Search","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":12},"by_repo_kind":{"listed":{"samples":15,"ran":3,"repositories":5}},"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":3,"samples":[{"code_sha256_prefix":"f34d83ec198f0b0c","entry":"calculate_loss","repo":"kayuksel/pytorch-ars","repo_kind":"listed","path":"ars_dataparallel.py","file_url":"https://github.com/kayuksel/pytorch-ars/blob/HEAD/ars_dataparallel.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f34d83ec198f0b0c"}},{"code_sha256_prefix":"bd8890576c4c1b92","entry":"get_batch","repo":"kayuksel/pytorch-ars","repo_kind":"listed","path":"ars_dataparallel.py","file_url":"https://github.com/kayuksel/pytorch-ars/blob/HEAD/ars_dataparallel.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"bd8890576c4c1b92"}},{"code_sha256_prefix":"6b3bc12652205efd","entry":"mkdir","repo":"jainpankul/Augmented-Random-Search","repo_kind":"listed","path":"ARS.py","file_url":"https://github.com/jainpankul/Augmented-Random-Search/blob/HEAD/ARS.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b3bc12652205efd"}},{"code_sha256_prefix":"00d0cc5eadefcd18","entry":"conv3x3","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/models/models.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/models/models.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":"00d0cc5eadefcd18"}},{"code_sha256_prefix":"49accadcbda40a13","entry":"convertImagePath","repo":"eric-erki/robotics-rl-srl","repo_kind":"listed","path":"environments/dataset_generator.py","file_url":"https://github.com/eric-erki/robotics-rl-srl/blob/HEAD/environments/dataset_generator.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":"49accadcbda40a13"}},{"code_sha256_prefix":"dfab5e99492d29c9","entry":"encodeOneHot","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/models/models.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/models/models.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":"dfab5e99492d29c9"}},{"code_sha256_prefix":"44c6ee6398a602b8","entry":"explore","repo":"suvhradipghosh07/Augmented-Random-Search","repo_kind":"listed","path":"_ai_.py","file_url":"https://github.com/suvhradipghosh07/Augmented-Random-Search/blob/HEAD/_ai_.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":"44c6ee6398a602b8"}},{"code_sha256_prefix":"fe771d1b728a1d21","entry":"findDissimilar","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/utils.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/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":"fe771d1b728a1d21"}},{"code_sha256_prefix":"61e7389045c32bd7","entry":"findSameActions","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/utils.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/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":"61e7389045c32bd7"}},{"code_sha256_prefix":"649af1e84314be4e","entry":"forwardModelLoss","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/losses.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/losses.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":"649af1e84314be4e"}},{"code_sha256_prefix":"305f5edcff073267","entry":"getSRLDim","repo":"eric-erki/robotics-rl-srl","repo_kind":"listed","path":"state_representation/models.py","file_url":"https://github.com/eric-erki/robotics-rl-srl/blob/HEAD/state_representation/models.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":"305f5edcff073267"}},{"code_sha256_prefix":"e44e088cf66053b3","entry":"inverseModelLoss","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/losses.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/losses.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":"e44e088cf66053b3"}},{"code_sha256_prefix":"5e577a99c2ee9cb3","entry":"overSampling","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/utils.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/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":"5e577a99c2ee9cb3"}},{"code_sha256_prefix":"171decf255010ed6","entry":"register","repo":"eric-erki/robotics-rl-srl","repo_kind":"listed","path":"environments/registry.py","file_url":"https://github.com/eric-erki/robotics-rl-srl/blob/HEAD/environments/registry.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":"171decf255010ed6"}},{"code_sha256_prefix":"4d38f7f1d06a5cfd","entry":"roboticPriorsLoss","repo":"billchan226/poar-srl-4-robot","repo_kind":"listed","path":"srl_zoo/losses/losses.py","file_url":"https://github.com/billchan226/poar-srl-4-robot/blob/HEAD/srl_zoo/losses/losses.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":"4d38f7f1d06a5cfd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}