{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","short_pith_number":"pith:OMTE3XG4","schema_version":"1.0","canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","source":{"kind":"arxiv","id":"2305.13795","version":2},"attestation_state":"computed","paper":{"title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksei Petrenko, Bryon Tjanaka, Gaurav Sukhatme, Matthew C. Fontaine, Stefanos Nikolaidis, Sumeet Batra","submitted_at":"2023-05-23T08:05:59Z","abstract_excerpt":"Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields -- Quality Diversity (QD) provides a principled form of exploration and produces collections of behaviorally diverse agents, while Reinforcement Learning (RL) provides a powerful performance improvement operator enabling generalization across tasks and dynamic environments. Existing QD-RL approaches have been constrained to samp"},"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":"2305.13795","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3","abstract_canon_sha256":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:50.743296Z","signature_b64":"K9YHWE0OorD/Re5UdZH6Mj599P1yKuIlqeg7vlwGhjVrCeMsH0BWcitunJAoDZsJxEZXdjO6LoZvav9T7HFQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","last_reissued_at":"2026-07-05T07:38:50.742743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:50.742743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksei Petrenko, Bryon Tjanaka, Gaurav Sukhatme, Matthew C. Fontaine, Stefanos Nikolaidis, Sumeet Batra","submitted_at":"2023-05-23T08:05:59Z","abstract_excerpt":"Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields -- Quality Diversity (QD) provides a principled form of exploration and produces collections of behaviorally diverse agents, while Reinforcement Learning (RL) provides a powerful performance improvement operator enabling generalization across tasks and dynamic environments. Existing QD-RL approaches have been constrained to samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13795","kind":"arxiv","version":2},"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/2305.13795/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":"2305.13795","created_at":"2026-07-05T07:38:50.742819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13795v2","created_at":"2026-07-05T07:38:50.742819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13795","created_at":"2026-07-05T07:38:50.742819+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMTE3XG4KEAD","created_at":"2026-07-05T07:38:50.742819+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMTE3XG4KEADLVHV","created_at":"2026-07-05T07:38:50.742819+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMTE3XG4","created_at":"2026-07-05T07:38:50.742819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20712","citing_title":"Multi-Objective Covariance Matrix Adaptation MAP-Annealing","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP","json":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP.json","graph_json":"https://pith.science/api/pith-number/OMTE3XG4KEADLVHVJR72VWRMHP/graph.json","events_json":"https://pith.science/api/pith-number/OMTE3XG4KEADLVHVJR72VWRMHP/events.json","paper":"https://pith.science/paper/OMTE3XG4"},"agent_actions":{"view_html":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP","download_json":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP.json","view_paper":"https://pith.science/paper/OMTE3XG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13795&json=true","fetch_graph":"https://pith.science/api/pith-number/OMTE3XG4KEADLVHVJR72VWRMHP/graph.json","fetch_events":"https://pith.science/api/pith-number/OMTE3XG4KEADLVHVJR72VWRMHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/action/storage_attestation","attest_author":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/action/author_attestation","sign_citation":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/action/citation_signature","submit_replication":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/action/replication_record"}},"created_at":"2026-07-05T07:38:50.742819+00:00","updated_at":"2026-07-05T07:38:50.742819+00:00"}