{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MMWBSR7XSB4JGCAJD2JA6YCRWF","short_pith_number":"pith:MMWBSR7X","schema_version":"1.0","canonical_sha256":"632c1947f790789308091e920f6051b15631a8686fcb4e15347841154200c0ee","source":{"kind":"arxiv","id":"2102.04376","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.04376","created_at":"2026-07-05T02:13:32.638930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04376v1","created_at":"2026-07-05T02:13:32.638930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04376","created_at":"2026-07-05T02:13:32.638930+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMWBSR7XSB4J","created_at":"2026-07-05T02:13:32.638930+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMWBSR7XSB4JGCAJ","created_at":"2026-07-05T02:13:32.638930+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMWBSR7X","created_at":"2026-07-05T02:13:32.638930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25438","citing_title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF","json":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF.json","graph_json":"https://pith.science/api/pith-number/MMWBSR7XSB4JGCAJD2JA6YCRWF/graph.json","events_json":"https://pith.science/api/pith-number/MMWBSR7XSB4JGCAJD2JA6YCRWF/events.json","paper":"https://pith.science/paper/MMWBSR7X"},"agent_actions":{"view_html":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF","download_json":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF.json","view_paper":"https://pith.science/paper/MMWBSR7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04376&json=true","fetch_graph":"https://pith.science/api/pith-number/MMWBSR7XSB4JGCAJD2JA6YCRWF/graph.json","fetch_events":"https://pith.science/api/pith-number/MMWBSR7XSB4JGCAJD2JA6YCRWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/action/storage_attestation","attest_author":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/action/author_attestation","sign_citation":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/action/citation_signature","submit_replication":"https://pith.science/pith/MMWBSR7XSB4JGCAJD2JA6YCRWF/action/replication_record"}},"created_at":"2026-07-05T02:13:32.638930+00:00","updated_at":"2026-07-05T02:13:32.638930+00:00"}