{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TUADVHD7DY3ZT5JD2CTHHLCIJE","short_pith_number":"pith:TUADVHD7","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"},"canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","source":{"kind":"arxiv","id":"2003.05334","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TUADVHD7DY3ZT5JD2CTHHLCIJE","target":"record","payload":{"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"},"canonical_sha256":"9d003a9c7f1e3799f523d0a673ac48491a2917fb4c83093f543562622fc72f3e","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"},"source_kind":"arxiv","source_id":"2003.05334","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OpfICSxp/Yao/sk77Qe7YGeIIQk5JtDkNjBxbqvY0aJXMCjov1cKJUFC9XgSOTVKyEHc4R30YdvZxS/bubHkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:44:19.089495Z"},"content_sha256":"6a77adb96c77c296ba75522e59b7dc0ce2fcc002fc0f748de00e3a279ab9c327","schema_version":"1.0","event_id":"sha256:6a77adb96c77c296ba75522e59b7dc0ce2fcc002fc0f748de00e3a279ab9c327"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TUADVHD7DY3ZT5JD2CTHHLCIJE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9OfxDeCZIM5NiF3/oTJLM/SRxOuGVcNDd7WoN5hQEoXNocgpYfvDcoiVu/CgVmFaPeMpzKcdHMAYGSwPeOalBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:44:19.090190Z"},"content_sha256":"cd2cb2fed80604cbec47cca9fe73cd365165f2b64f89b9948562e21f5d2fdf14","schema_version":"1.0","event_id":"sha256:cd2cb2fed80604cbec47cca9fe73cd365165f2b64f89b9948562e21f5d2fdf14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/bundle.json","state_url":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T22:44:19Z","links":{"resolver":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE","bundle":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/bundle.json","state":"https://pith.science/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUADVHD7DY3ZT5JD2CTHHLCIJE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2t+JawiHsEjQKHPh4kNPj9WSx1v/1DHIaOVtopGbhZAqUvfZWZBczge+IBlhEzEQXI8gxXyuWmbPvOZwxpgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:44:19.095486Z","bundle_sha256":"b2dcbf3fa2e4fa2bcbf5a56368ffb82f6e54c2c09ffe0c2ad83059e4e49fa598"}}