{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TUADVHD7DY3ZT5JD2CTHHLCIJE","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":"64eb5dee507f24a51f6fbf346884cd9538bd59880846f471932d91a2f8a0af6b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:39:49Z","title_canon_sha256":"f3ae7f789744bfcde6ee6d4f823d09f8363cf980a1d5f918ee3901e49ccecd6b"},"schema_version":"1.0","source":{"id":"2003.05334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05334","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05334v2","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05334","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"TUADVHD7DY3Z","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"TUADVHD7DY3ZT5JD","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"TUADVHD7","created_at":"2026-07-05T01:48:08Z"}],"graph_snapshots":[{"event_id":"sha256:cd2cb2fed80604cbec47cca9fe73cd365165f2b64f89b9948562e21f5d2fdf14","target":"graph","created_at":"2026-07-05T01:48:08Z","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/2003.05334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the actor that trains it to take actions with higher expected return. In this paper, we introduce a novel and flexible meta-critic that observes the learning process and meta-learns an additional loss for the actor that accelerates and improves actor-critic learning. Compared to the vanilla critic, the meta-critic network is explicitly trained to accelerate the lea","authors_text":"Huaimin Wang, Timothy M. Hospedales, Wei Zhou, Yiying Li, Yongxin Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:39:49Z","title":"Online Meta-Critic Learning for Off-Policy Actor-Critic Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05334","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":"sha256:6a77adb96c77c296ba75522e59b7dc0ce2fcc002fc0f748de00e3a279ab9c327","target":"record","created_at":"2026-07-05T01:48:08Z","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":"64eb5dee507f24a51f6fbf346884cd9538bd59880846f471932d91a2f8a0af6b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:39:49Z","title_canon_sha256":"f3ae7f789744bfcde6ee6d4f823d09f8363cf980a1d5f918ee3901e49ccecd6b"},"schema_version":"1.0","source":{"id":"2003.05334","kind":"arxiv","version":2}},"canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","first_computed_at":"2026-07-05T01:48:08.239003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:08.239003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeOol0lvkYqch1V/s/vbam3Xl6b+YlKxAejqYGZeMe/vXV8TVUKfJDJ3KsH1G90NOHPxRUwMBQciGXBVSVFhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:08.239368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.05334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a77adb96c77c296ba75522e59b7dc0ce2fcc002fc0f748de00e3a279ab9c327","sha256:cd2cb2fed80604cbec47cca9fe73cd365165f2b64f89b9948562e21f5d2fdf14"],"state_sha256":"6728768bc04f5593fa473f4b62ea1d51fbf8ae83d427fd96fe767006649559ba"}