{"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/dep-rl-embodied-exploration-for-reinforcement","title":"DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems","arxiv_id":"2206.00484","date":"2022-05-30","proceeding":null,"authors":["Pierre Schumacher","Daniel Häufle","Dieter Büchler","Syn Schmitt","Georg Martius"],"abstract":"Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large musculoskeletal models, however, has not been able to show similar performance. We conjecture that ineffective exploration in large overactuated action spaces is a key problem. This is supported by the finding that common exploration noise strategies are inadequate in synthetic examples of overactuated systems. We identify differential extrinsic plasticity (DEP), a method from the domain of self-organization, as being able to induce state-space covering exploration within seconds of interaction. By integrating DEP into RL, we achieve fast learning of reaching and locomotion in musculoskeletal systems, outperforming current approaches in all considered tasks in sample efficiency and robustness.","url_abs":"https://arxiv.org/abs/2206.00484v2","url_pdf":"https://arxiv.org/pdf/2206.00484v2.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":"dep-rl-embodied-exploration-for-reinforcement","repo_url":"https://github.com/martius-lab/depRL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.00484","atlas_url":"https://app.syntology.ai/?focus=2206.00484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00484"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/martius-lab/depRL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"6e825a9bd6f6bcd0","entry":"get_paths","repo":"martius-lab/depRL","repo_kind":"official","path":"deprl/play.py","file_url":"https://github.com/martius-lab/depRL/blob/HEAD/deprl/play.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":true,"mcp_get_code":{"code_sha256":"6e825a9bd6f6bcd0"}},{"code_sha256_prefix":"6bb6ff992c4cc6fc","entry":"build_env_from_dict","repo":"martius-lab/depRL","repo_kind":"official","path":"deprl/custom_distributed.py","file_url":"https://github.com/martius-lab/depRL/blob/HEAD/deprl/custom_distributed.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":"6bb6ff992c4cc6fc"}},{"code_sha256_prefix":"6861237270bcb93e","entry":"dep_factory","repo":"martius-lab/depRL","repo_kind":"official","path":"deprl/custom_agents.py","file_url":"https://github.com/martius-lab/depRL/blob/HEAD/deprl/custom_agents.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":"6861237270bcb93e"}},{"code_sha256_prefix":"095bd917a5787899","entry":"play_control_suite","repo":"martius-lab/depRL","repo_kind":"official","path":"deprl/play.py","file_url":"https://github.com/martius-lab/depRL/blob/HEAD/deprl/play.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":"095bd917a5787899"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}