{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OEKAA5PDAE3CYVCLNHK7UEXRFD","short_pith_number":"pith:OEKAA5PD","schema_version":"1.0","canonical_sha256":"71140075e301362c544b69d5fa12f128f79266ec1a9335b89bc76ed430a559cb","source":{"kind":"arxiv","id":"2210.03516","version":4},"attestation_state":"computed","paper":{"title":"Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Antoine Cully, Arthur Flajolet, Bryan Lim, Felix Chalumeau, Maxime Allard, Raphael Boige, Thomas Pierrot, Valentin Mac\\'e","submitted_at":"2022-10-06T11:06:39Z","abstract_excerpt":"Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were trained on, and thus do not perform well when conditions deviate slightly or when composed hierarchically to solve even more complex tasks. Recent work has shown that training a mixture of policies, as opposed to a single one, that are driven to explore different regions of the state-action space can address this shortcoming by generating a diverse set of beha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.03516","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-10-06T11:06:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4e8656416643e283e032641e977671dcf2263b5ab98a33ce26d249f9bdcd8cde","abstract_canon_sha256":"f249157fd76bf102973c9f4b97a64fe1733a48f5ed1a7e96e97f9388039a14e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:45.954064Z","signature_b64":"o59Yrq7XN4jjSS7NkpSf6KsH7+Um/bZkuFjbxzkdvX/LjJyaiFQPdtC3shl69uPxOVqy7IZ8IOUkQxFoPtPkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71140075e301362c544b69d5fa12f128f79266ec1a9335b89bc76ed430a559cb","last_reissued_at":"2026-07-05T06:48:45.953507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:45.953507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Antoine Cully, Arthur Flajolet, Bryan Lim, Felix Chalumeau, Maxime Allard, Raphael Boige, Thomas Pierrot, Valentin Mac\\'e","submitted_at":"2022-10-06T11:06:39Z","abstract_excerpt":"Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were trained on, and thus do not perform well when conditions deviate slightly or when composed hierarchically to solve even more complex tasks. Recent work has shown that training a mixture of policies, as opposed to a single one, that are driven to explore different regions of the state-action space can address this shortcoming by generating a diverse set of beha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03516","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.03516/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.03516","created_at":"2026-07-05T06:48:45.953573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03516v4","created_at":"2026-07-05T06:48:45.953573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03516","created_at":"2026-07-05T06:48:45.953573+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEKAA5PDAE3C","created_at":"2026-07-05T06:48:45.953573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEKAA5PDAE3CYVCL","created_at":"2026-07-05T06:48:45.953573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEKAA5PD","created_at":"2026-07-05T06:48:45.953573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15414","citing_title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD","json":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD.json","graph_json":"https://pith.science/api/pith-number/OEKAA5PDAE3CYVCLNHK7UEXRFD/graph.json","events_json":"https://pith.science/api/pith-number/OEKAA5PDAE3CYVCLNHK7UEXRFD/events.json","paper":"https://pith.science/paper/OEKAA5PD"},"agent_actions":{"view_html":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD","download_json":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD.json","view_paper":"https://pith.science/paper/OEKAA5PD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03516&json=true","fetch_graph":"https://pith.science/api/pith-number/OEKAA5PDAE3CYVCLNHK7UEXRFD/graph.json","fetch_events":"https://pith.science/api/pith-number/OEKAA5PDAE3CYVCLNHK7UEXRFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD/action/storage_attestation","attest_author":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD/action/author_attestation","sign_citation":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD/action/citation_signature","submit_replication":"https://pith.science/pith/OEKAA5PDAE3CYVCLNHK7UEXRFD/action/replication_record"}},"created_at":"2026-07-05T06:48:45.953573+00:00","updated_at":"2026-07-05T06:48:45.953573+00:00"}