{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GF23IHZDJ7CKKXW564JYKVGTTB","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":"6c8a831dfc1277ba0987c4ca61f24a20155abc7a43d907ba9cae7d878004b409","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T00:09:47Z","title_canon_sha256":"43a71291deb8cef1f27a5faeb7d99873517f96175425bed7e80b803571da1354"},"schema_version":"1.0","source":{"id":"2403.09930","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09930","created_at":"2026-07-05T08:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09930v3","created_at":"2026-07-05T08:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09930","created_at":"2026-07-05T08:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"GF23IHZDJ7CK","created_at":"2026-07-05T08:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"GF23IHZDJ7CKKXW5","created_at":"2026-07-05T08:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"GF23IHZD","created_at":"2026-07-05T08:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:d623a2535fba449499b1edc5f3c7fcd5f9f22e4e57aed9815d5c0eb70bbd9fed","target":"graph","created_at":"2026-07-05T08:26:21Z","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/2403.09930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return only one solution specialized for a specific problem. We introduce Quality-Diversity Actor-Critic (QDAC), an off-policy actor-critic deep reinforcement learning algorithm that leverages a value function critic and a successor features critic to learn high-performing and diverse behaviors. I","authors_text":"Antoine Cully, Borja G. Le\\'on, Luca Grillotti, Maxence Faldor","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T00:09:47Z","title":"Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09930","kind":"arxiv","version":3},"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:d46f03c0519faa994a9646e906b842432eec9b93b0deeb97654bc4b21e2957a7","target":"record","created_at":"2026-07-05T08:26:21Z","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":"6c8a831dfc1277ba0987c4ca61f24a20155abc7a43d907ba9cae7d878004b409","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T00:09:47Z","title_canon_sha256":"43a71291deb8cef1f27a5faeb7d99873517f96175425bed7e80b803571da1354"},"schema_version":"1.0","source":{"id":"2403.09930","kind":"arxiv","version":3}},"canonical_sha256":"3175b41f234fc4a55eddf7138554d3986ad532940ac4398f7e3de049b4a0bc3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3175b41f234fc4a55eddf7138554d3986ad532940ac4398f7e3de049b4a0bc3d","first_computed_at":"2026-07-05T08:26:21.775920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:21.775920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ao+GptvJvzWHl7JqR7/811SMvTcZMfi+vs9gtOlE3JtkWubpdYVo7JEBxWXCFIPYbkofJHrIN+rNycwmY4jeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:21.776383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09930","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d46f03c0519faa994a9646e906b842432eec9b93b0deeb97654bc4b21e2957a7","sha256:d623a2535fba449499b1edc5f3c7fcd5f9f22e4e57aed9815d5c0eb70bbd9fed"],"state_sha256":"9889ad53bba68e8b004ac3299791a89df38f40439cc6b5686fd1ef68cb833127"}