{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3"},"schema_version":"1.0","source":{"id":"2305.13795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13795v2","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"OMTE3XG4KEAD","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"OMTE3XG4KEADLVHV","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"OMTE3XG4","created_at":"2026-07-05T07:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d","target":"graph","created_at":"2026-07-05T07:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aleksei Petrenko, Bryon Tjanaka, Gaurav Sukhatme, Matthew C. Fontaine, Stefanos Nikolaidis, Sumeet Batra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13795","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b","target":"record","created_at":"2026-07-05T07:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3"},"schema_version":"1.0","source":{"id":"2305.13795","kind":"arxiv","version":2}},"canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","first_computed_at":"2026-07-05T07:38:50.742743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:50.742743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K9YHWE0OorD/Re5UdZH6Mj599P1yKuIlqeg7vlwGhjVrCeMsH0BWcitunJAoDZsJxEZXdjO6LoZvav9T7HFQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:50.743296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b","sha256:3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d"],"state_sha256":"3c92fc350e572c10791600917b5947020136c22d4abd886b3b4ee0c8d515f31f"}