{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TUADVHD7DY3ZT5JD2CTHHLCIJE","short_pith_number":"pith:TUADVHD7","schema_version":"1.0","canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","source":{"kind":"arxiv","id":"2003.05334","version":2},"attestation_state":"computed","paper":{"title":"Online Meta-Critic Learning for Off-Policy Actor-Critic Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huaimin Wang, Timothy M. Hospedales, Wei Zhou, Yiying Li, Yongxin Yang","submitted_at":"2020-03-11T14:39:49Z","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"},"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":"2003.05334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-11T14:39:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f3ae7f789744bfcde6ee6d4f823d09f8363cf980a1d5f918ee3901e49ccecd6b","abstract_canon_sha256":"64eb5dee507f24a51f6fbf346884cd9538bd59880846f471932d91a2f8a0af6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:08.239368Z","signature_b64":"jeOol0lvkYqch1V/s/vbam3Xl6b+YlKxAejqYGZeMe/vXV8TVUKfJDJ3KsH1G90NOHPxRUwMBQciGXBVSVFhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","last_reissued_at":"2026-07-05T01:48:08.239003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:08.239003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Meta-Critic Learning for Off-Policy Actor-Critic Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huaimin Wang, Timothy M. Hospedales, Wei Zhou, Yiying Li, Yongxin Yang","submitted_at":"2020-03-11T14:39:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05334","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/2003.05334/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":"2003.05334","created_at":"2026-07-05T01:48:08.239067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.05334v2","created_at":"2026-07-05T01:48:08.239067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05334","created_at":"2026-07-05T01:48:08.239067+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUADVHD7DY3Z","created_at":"2026-07-05T01:48:08.239067+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUADVHD7DY3ZT5JD","created_at":"2026-07-05T01:48:08.239067+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUADVHD7","created_at":"2026-07-05T01:48:08.239067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE","json":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE.json","graph_json":"https://pith.science/api/pith-number/TUADVHD7DY3ZT5JD2CTHHLCIJE/graph.json","events_json":"https://pith.science/api/pith-number/TUADVHD7DY3ZT5JD2CTHHLCIJE/events.json","paper":"https://pith.science/paper/TUADVHD7"},"agent_actions":{"view_html":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE","download_json":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE.json","view_paper":"https://pith.science/paper/TUADVHD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.05334&json=true","fetch_graph":"https://pith.science/api/pith-number/TUADVHD7DY3ZT5JD2CTHHLCIJE/graph.json","fetch_events":"https://pith.science/api/pith-number/TUADVHD7DY3ZT5JD2CTHHLCIJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/action/storage_attestation","attest_author":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/action/author_attestation","sign_citation":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/action/citation_signature","submit_replication":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/action/replication_record"}},"created_at":"2026-07-05T01:48:08.239067+00:00","updated_at":"2026-07-05T01:48:08.239067+00:00"}