{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MMWBSR7XSB4JGCAJD2JA6YCRWF","short_pith_number":"pith:MMWBSR7X","canonical_record":{"source":{"id":"2102.04376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T17:31:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"852a6750373f28e072d484562e84cebd63c225ae44d304daed1543e89deef9bf","abstract_canon_sha256":"68d4e882d830ecc1bbf65fafcd926cc06e12fdda68b81a19676a8f64fc2bdb68"},"schema_version":"1.0"},"canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","source":{"kind":"arxiv","id":"2102.04376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04376","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04376v1","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04376","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"MMWBSR7XSB4J","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"MMWBSR7XSB4JGCAJ","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"MMWBSR7X","created_at":"2026-07-05T02:13:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MMWBSR7XSB4JGCAJD2JA6YCRWF","target":"record","payload":{"canonical_record":{"source":{"id":"2102.04376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T17:31:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"852a6750373f28e072d484562e84cebd63c225ae44d304daed1543e89deef9bf","abstract_canon_sha256":"68d4e882d830ecc1bbf65fafcd926cc06e12fdda68b81a19676a8f64fc2bdb68"},"schema_version":"1.0"},"canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:32.639281Z","signature_b64":"PiEEd3CgEPmO5RjPS6e2R9o5LXU7LSEJLdrpHqhOQmqtzb1Dc8yrA+bFP3IUYg1Mo9WmYcskSKoKbL+gdFRcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","last_reissued_at":"2026-07-05T02:13:32.638871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:32.638871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.04376","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":"2026-07-05T02:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6E6t2FVPTOWQUxqWPu9RXO/mJzfnn/CNmjgofxRf/VRXJhrbqr8OIlA/J7gv3dKCukWnNqv3Q53OJDZHhEACAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:38:10.802737Z"},"content_sha256":"df800cd34fcb2d0d6c5f296f4753ae765c1775645980ec0b423019be69b76dd3","schema_version":"1.0","event_id":"sha256:df800cd34fcb2d0d6c5f296f4753ae765c1775645980ec0b423019be69b76dd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MMWBSR7XSB4JGCAJD2JA6YCRWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarially Guided Actor-Critic","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Johan Ferret, Matthieu Geist, Olivier Pietquin, Philippe Preux, Yannis Flet-Berliac","submitted_at":"2021-02-08T17:31:13Z","abstract_excerpt":"Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These methods consider a policy (the actor) and a value function (the critic) whose respective losses are built using different motivations and approaches. This paper introduces a third protagonist: the adversary. While the adversary mimics the actor by minimizing the KL-divergence between their respective action distributions, the actor, in addition to learning to solv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04376","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.04376/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":"2026-07-05T02:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUkfLzyUn3XFK82QG+lvPyhmMg6Z4o34HmtionNJUuPsZrT6evf6FJ1M7bJiGyssOpY96QqsNP+463byo+RNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:38:10.804391Z"},"content_sha256":"62d367c7d1194e3c2ab28ac09593ce5348ce1c0b56bcba6eca5e14726c12c375","schema_version":"1.0","event_id":"sha256:62d367c7d1194e3c2ab28ac09593ce5348ce1c0b56bcba6eca5e14726c12c375"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/bundle.json","state_url":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/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":"2026-08-20T10:38:10Z","links":{"resolver":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF","bundle":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/bundle.json","state":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MMWBSR7XSB4JGCAJD2JA6YCRWF","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":"68d4e882d830ecc1bbf65fafcd926cc06e12fdda68b81a19676a8f64fc2bdb68","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T17:31:13Z","title_canon_sha256":"852a6750373f28e072d484562e84cebd63c225ae44d304daed1543e89deef9bf"},"schema_version":"1.0","source":{"id":"2102.04376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04376","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04376v1","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04376","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"MMWBSR7XSB4J","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"MMWBSR7XSB4JGCAJ","created_at":"2026-07-05T02:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"MMWBSR7X","created_at":"2026-07-05T02:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:62d367c7d1194e3c2ab28ac09593ce5348ce1c0b56bcba6eca5e14726c12c375","target":"graph","created_at":"2026-07-05T02:13:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.04376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck. These methods consider a policy (the actor) and a value function (the critic) whose respective losses are built using different motivations and approaches. This paper introduces a third protagonist: the adversary. While the adversary mimics the actor by minimizing the KL-divergence between their respective action distributions, the actor, in addition to learning to solv","authors_text":"Johan Ferret, Matthieu Geist, Olivier Pietquin, Philippe Preux, Yannis Flet-Berliac","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T17:31:13Z","title":"Adversarially Guided Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04376","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:df800cd34fcb2d0d6c5f296f4753ae765c1775645980ec0b423019be69b76dd3","target":"record","created_at":"2026-07-05T02:13:32Z","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":"68d4e882d830ecc1bbf65fafcd926cc06e12fdda68b81a19676a8f64fc2bdb68","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T17:31:13Z","title_canon_sha256":"852a6750373f28e072d484562e84cebd63c225ae44d304daed1543e89deef9bf"},"schema_version":"1.0","source":{"id":"2102.04376","kind":"arxiv","version":1}},"canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","first_computed_at":"2026-07-05T02:13:32.638871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:32.638871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PiEEd3CgEPmO5RjPS6e2R9o5LXU7LSEJLdrpHqhOQmqtzb1Dc8yrA+bFP3IUYg1Mo9WmYcskSKoKbL+gdFRcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:32.639281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df800cd34fcb2d0d6c5f296f4753ae765c1775645980ec0b423019be69b76dd3","sha256:62d367c7d1194e3c2ab28ac09593ce5348ce1c0b56bcba6eca5e14726c12c375"],"state_sha256":"121c87bab69e8ae2104bf91d14255b7c9bb489360007f86b25389fb69a969f2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnt3siTmkYv0AVTzqlGAUFzrYn57rE16+V1/H1CvWaWTUL1LAKGIBtYfJCS5Ozs24t1Xf5lYLiUywenLYufSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:38:10.809770Z","bundle_sha256":"dbe3be11b298e03d672f6e78838b6e11b09c7757a7d2567079670544997da0b9"}}