{"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/controllability-aware-unsupervised-skill","title":"Controllability-Aware Unsupervised Skill Discovery","arxiv_id":"2302.05103","date":"2023-02-10","proceeding":null,"authors":["Seohong Park","Kimin Lee","Youngwoon Lee","Pieter Abbeel"],"abstract":"One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods are often limited to acquiring simple, easy-to-learn skills due to the lack of incentives to discover more complex, challenging behaviors. We introduce a novel unsupervised skill discovery method, Controllability-aware Skill Discovery (CSD), which actively seeks complex, hard-to-control skills without supervision. The key component of CSD is a controllability-aware distance function, which assigns larger values to state transitions that are harder to achieve with the current skills. Combined with distance-maximizing skill discovery, CSD progressively learns more challenging skills over the course of training as our jointly trained distance function reduces rewards for easy-to-achieve skills. Our experimental results in six robotic manipulation and locomotion environments demonstrate that CSD can discover diverse complex skills including object manipulation and locomotion skills with no supervision, significantly outperforming prior unsupervised skill discovery methods. Videos and code are available at https://seohong.me/projects/csd/","url_abs":"https://arxiv.org/abs/2302.05103v3","url_pdf":"https://arxiv.org/pdf/2302.05103v3.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":"controllability-aware-unsupervised-skill","repo_url":"https://github.com/artberryx/csd-public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"controllability-aware-unsupervised-skill","repo_url":"https://github.com/seohongpark/csd-locomotion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"controllability-aware-unsupervised-skill","repo_url":"https://github.com/seohongpark/CSD-manipulation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.05103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05103"}},"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/artberryx/csd-public","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seohongpark/CSD-manipulation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seohongpark/csd-locomotion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_violates":1,"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"repositories":3}},"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":"ea62c621866571a4","entry":"get_2d_colors","repo":"seohongpark/csd-manipulation","repo_kind":"official","path":"utils.py","file_url":"https://github.com/seohongpark/csd-manipulation/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea62c621866571a4"}},{"code_sha256_prefix":"eacc7920f6eceaf0","entry":"get_option_colors","repo":"seohongpark/csd-manipulation","repo_kind":"official","path":"utils.py","file_url":"https://github.com/seohongpark/csd-manipulation/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eacc7920f6eceaf0"}},{"code_sha256_prefix":"e47eba06f6824dbd","entry":"l2_norm","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e47eba06f6824dbd"}},{"code_sha256_prefix":"16ebb9997d99bab8","entry":"setup_evaluation","repo":"seohongpark/csd-manipulation","repo_kind":"official","path":"utils.py","file_url":"https://github.com/seohongpark/csd-manipulation/blob/HEAD/utils.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16ebb9997d99bab8"}},{"code_sha256_prefix":"ce82cd8ce37faf68","entry":"spectral_norm","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce82cd8ce37faf68"}},{"code_sha256_prefix":"d123b177811d57b3","entry":"store_args","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d123b177811d57b3"}},{"code_sha256_prefix":"6791c540f021f7a6","entry":"Discriminator","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.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":true,"mcp_get_code":{"code_sha256":"6791c540f021f7a6"}},{"code_sha256_prefix":"68a57588acd1e63a","entry":"colorize","repo":"seohongpark/csd-locomotion","repo_kind":"official","path":"dowel/utils.py","file_url":"https://github.com/seohongpark/csd-locomotion/blob/HEAD/dowel/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":"68a57588acd1e63a"}},{"code_sha256_prefix":"e51948cd326a355e","entry":"fully_conneted","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.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":true,"mcp_get_code":{"code_sha256":"e51948cd326a355e"}},{"code_sha256_prefix":"fa9fb1b4a96d224b","entry":"snn","repo":"artberryx/csd-public","repo_kind":"official","path":"baselines/her/discriminator.py","file_url":"https://github.com/artberryx/csd-public/blob/HEAD/baselines/her/discriminator.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":true,"mcp_get_code":{"code_sha256":"fa9fb1b4a96d224b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}