{"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/190504100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","arxiv_id":"1905.04100","date":"2019-02-19","proceeding":null,"authors":["Adarsh Sehgal","Hung Manh La","Sushil J. Louis","Hai Nguyen"],"abstract":"Reinforcement learning (RL) enables agents to take decision based on a reward\nfunction. However, in the process of learning, the choice of values for\nlearning algorithm parameters can significantly impact the overall learning\nprocess. In this paper, we use a genetic algorithm (GA) to find the values of\nparameters used in Deep Deterministic Policy Gradient (DDPG) combined with\nHindsight Experience Replay (HER), to help speed up the learning agent. We used\nthis method on fetch-reach, slide, push, pick and place, and door opening in\nrobotic manipulation tasks. Our experimental evaluation shows that our method\nleads to better performance, faster than the original algorithm.","url_abs":"http://arxiv.org/abs/1905.04100v1","url_pdf":"http://arxiv.org/pdf/1905.04100v1.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":"190504100","repo_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190504100","repo_url":"https://github.com/Bibyutatsu/Self_Driving_Car","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1905.04100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04100"}},"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/Bibyutatsu/Self_Driving_Car","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aralab-unr/ReinforcementLearningWithGA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":2,"unverified":10},"by_repo_kind":{"official":{"samples":12,"ran":2,"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":13,"samples":[{"code_sha256_prefix":"98948fae5be7e92e","entry":"profile","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/logger.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"98948fae5be7e92e"}},{"code_sha256_prefix":"a44574392d168384","entry":"register","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/common/models.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/common/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a44574392d168384"}},{"code_sha256_prefix":"dac1c1782a9dfe5d","entry":"uncompress_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dac1c1782a9dfe5d"}},{"code_sha256_prefix":"a3b4038f4e9b9479","entry":"cat_entropy","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/a2c/utils.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/a2c/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":"a3b4038f4e9b9479"}},{"code_sha256_prefix":"7082b4bbc0d9384f","entry":"cat_entropy_softmax","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/a2c/utils.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/a2c/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":"7082b4bbc0d9384f"}},{"code_sha256_prefix":"7d1de6cac3908eed","entry":"decode_function","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"ga.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/ga.py","link_basis":"first_harvest_node","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":"7d1de6cac3908eed"}},{"code_sha256_prefix":"7a93f8d2f700541b","entry":"fitness_function","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"ga.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/ga.py","link_basis":"first_harvest_node","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":"7a93f8d2f700541b"}},{"code_sha256_prefix":"28dc605330336da2","entry":"make_output_format","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/logger.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":"28dc605330336da2"}},{"code_sha256_prefix":"88ef5a17fc986d9a","entry":"read_json","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/logger.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/logger.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":"88ef5a17fc986d9a"}},{"code_sha256_prefix":"895ca4b776fb6d6d","entry":"rolling_window","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/results_plotter.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/results_plotter.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":"895ca4b776fb6d6d"}},{"code_sha256_prefix":"178099b1f8fb2b9d","entry":"sample","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/a2c/utils.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/a2c/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":"178099b1f8fb2b9d"}},{"code_sha256_prefix":"4ab4ad5ff9820e39","entry":"ts2xy","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/results_plotter.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/results_plotter.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":"4ab4ad5ff9820e39"}},{"code_sha256_prefix":"43741b9339bd80da","entry":"window_func","repo":"aralab-unr/ReinforcementLearningWithGA","repo_kind":"official","path":"baselines/results_plotter.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/results_plotter.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":"43741b9339bd80da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}