{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:74LJ2JO24GFHKNYZNRZF2K4I3N","short_pith_number":"pith:74LJ2JO2","canonical_record":{"source":{"id":"1902.02556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-07T10:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"cba0b5779067aec989dfcbb2b9fd9aeb3e6aade9f1fb06de60fb1f342dbcf636","abstract_canon_sha256":"c4b19b28b8e57c2557f2af85866df4eb7749c07c6afd9ba922c21b84c07a3aff"},"schema_version":"1.0"},"canonical_sha256":"ff169d25dae18a7537196c725d2b88db5a773ebdf6ddf7ed3bc4aceda7cfe26b","source":{"kind":"arxiv","id":"1902.02556","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02556","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02556v1","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02556","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"74LJ2JO24GFH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"74LJ2JO24GFHKNYZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"74LJ2JO2","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:74LJ2JO24GFHKNYZNRZF2K4I3N","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-07T10:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"cba0b5779067aec989dfcbb2b9fd9aeb3e6aade9f1fb06de60fb1f342dbcf636","abstract_canon_sha256":"c4b19b28b8e57c2557f2af85866df4eb7749c07c6afd9ba922c21b84c07a3aff"},"schema_version":"1.0"},"canonical_sha256":"ff169d25dae18a7537196c725d2b88db5a773ebdf6ddf7ed3bc4aceda7cfe26b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:32.882932Z","signature_b64":"N09/THaWKkfa1FXJcggMaXb8kFeXPOTYRJLolv1VMzAEB8asOg8De8sn6PyZRDgu7xMNtpNpeqk8bgZWHOTBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff169d25dae18a7537196c725d2b88db5a773ebdf6ddf7ed3bc4aceda7cfe26b","last_reissued_at":"2026-05-17T23:54:32.882387Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:32.882387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02556","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CK1+SboE2SBnsTRLDs0r2Wd7Zy8v11L+evwPF6cB5R1A5zB9mcPaJ+3HEYkHPKirIEpy2I/W2dV1aPiU5HlzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:30:03.452852Z"},"content_sha256":"3274884d5241523e3bec10396f3f4a4e5d513c60f6d67d2d03425e236de4d799","schema_version":"1.0","event_id":"sha256:3274884d5241523e3bec10396f3f4a4e5d513c60f6d67d2d03425e236de4d799"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:74LJ2JO24GFHKNYZNRZF2K4I3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Actor-Advisor: Policy Gradient With Off-Policy Advice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier","submitted_at":"2019-02-07T10:30:40Z","abstract_excerpt":"Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability and promising convergence properties, current actor-critic algorithms do not outperform critic-only ones in practice. We believe that the fact that the critic learns Q^pi, instead of the optimal Q-function Q*, prevents state-of-the-art robust and sample-efficient off-policy learning algorithms from being used. In this paper, we propose an elegant solution, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02556","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aV0Zh4A9ZkO9atRRxTmZ+nrICT3NRLvr78lk1Rs3+ADPH0WqIudKSGRG7HhJEZA6itY7a7zsOF1f7LHEyga3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:30:03.453197Z"},"content_sha256":"147ffe610f6b74dba1abb21b2e113c2c55890d82613a40203582bb434b44977b","schema_version":"1.0","event_id":"sha256:147ffe610f6b74dba1abb21b2e113c2c55890d82613a40203582bb434b44977b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/bundle.json","state_url":"https://pith.science/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/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":"2026-06-02T15:30:03Z","links":{"resolver":"https://pith.science/pith/74LJ2JO24GFHKNYZNRZF2K4I3N","bundle":"https://pith.science/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/bundle.json","state":"https://pith.science/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74LJ2JO24GFHKNYZNRZF2K4I3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:74LJ2JO24GFHKNYZNRZF2K4I3N","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":"c4b19b28b8e57c2557f2af85866df4eb7749c07c6afd9ba922c21b84c07a3aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-07T10:30:40Z","title_canon_sha256":"cba0b5779067aec989dfcbb2b9fd9aeb3e6aade9f1fb06de60fb1f342dbcf636"},"schema_version":"1.0","source":{"id":"1902.02556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02556","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02556v1","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02556","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"74LJ2JO24GFH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"74LJ2JO24GFHKNYZ","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"74LJ2JO2","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:147ffe610f6b74dba1abb21b2e113c2c55890d82613a40203582bb434b44977b","target":"graph","created_at":"2026-05-17T23:54:32Z","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"},"paper":{"abstract_excerpt":"Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor's current policy. However, despite their stability and promising convergence properties, current actor-critic algorithms do not outperform critic-only ones in practice. We believe that the fact that the critic learns Q^pi, instead of the optimal Q-function Q*, prevents state-of-the-art robust and sample-efficient off-policy learning algorithms from being used. In this paper, we propose an elegant solution, the","authors_text":"Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-07T10:30:40Z","title":"The Actor-Advisor: Policy Gradient With Off-Policy Advice"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02556","kind":"arxiv","version":1},"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":"sha256:3274884d5241523e3bec10396f3f4a4e5d513c60f6d67d2d03425e236de4d799","target":"record","created_at":"2026-05-17T23:54:32Z","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":"c4b19b28b8e57c2557f2af85866df4eb7749c07c6afd9ba922c21b84c07a3aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-07T10:30:40Z","title_canon_sha256":"cba0b5779067aec989dfcbb2b9fd9aeb3e6aade9f1fb06de60fb1f342dbcf636"},"schema_version":"1.0","source":{"id":"1902.02556","kind":"arxiv","version":1}},"canonical_sha256":"ff169d25dae18a7537196c725d2b88db5a773ebdf6ddf7ed3bc4aceda7cfe26b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff169d25dae18a7537196c725d2b88db5a773ebdf6ddf7ed3bc4aceda7cfe26b","first_computed_at":"2026-05-17T23:54:32.882387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:32.882387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N09/THaWKkfa1FXJcggMaXb8kFeXPOTYRJLolv1VMzAEB8asOg8De8sn6PyZRDgu7xMNtpNpeqk8bgZWHOTBAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:32.882932Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3274884d5241523e3bec10396f3f4a4e5d513c60f6d67d2d03425e236de4d799","sha256:147ffe610f6b74dba1abb21b2e113c2c55890d82613a40203582bb434b44977b"],"state_sha256":"2bd3c978ec522a920c6bf1883ae5ae2fad6e6c82f3e6bbc3ec4717d99ee62d7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dek6Mv5CoKy94Iy+N2nN1kgbe2pXGBcPam5FUVSL3Y3D6xbcuvfWR+HNKj7j7hCNkk0sQACuHUddL+XDWEJeAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:30:03.455364Z","bundle_sha256":"aa8728f0d100a1712327673f97b92b1de5e03cc93fc805b7bc6ace4238457f02"}}