{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F22XKRM75OGKA4GEKJVEEP7CML","short_pith_number":"pith:F22XKRM7","schema_version":"1.0","canonical_sha256":"2eb575459feb8ca070c4526a423fe262c539f474273dc7c63270c6ac238042c0","source":{"kind":"arxiv","id":"2403.00514","version":2},"attestation_state":"computed","paper":{"title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marek Cygan, Mateusz Ostaszewski, Micha{\\l} Bortkiewicz, Michal Nauman, Piotr Mi{\\l}o\\'s, Tomasz Trzci\\'nski","submitted_at":"2024-03-01T13:25:10Z","abstract_excerpt":"Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional agents. However, many of these techniques have been tested in limited settings, often on tasks from single simulation benchmarks and against well-known algorithms rather than a range of regularization approaches. This limits our understanding of the specific mechanisms driving RL improvements. To address this, we implemented over 60 different off-policy agents, e"},"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":"2403.00514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T13:25:10Z","cross_cats_sorted":[],"title_canon_sha256":"84bc92c5f5f2c53edbe98ca8b9ca9677f832c101df204c6b45af35da0e134d76","abstract_canon_sha256":"056a027245fb40b1bd6bf09286d56926507db9c407a5fd2db1c6a4e711f0201b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:14.680392Z","signature_b64":"2WwaniCoE/HP+6bqo77p1BFhz/bKrCTaSjNw2sTIGb8NqLG5Fd17LDYU43NknFIoR5wvlOJ2UYQM2FslOHnNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eb575459feb8ca070c4526a423fe262c539f474273dc7c63270c6ac238042c0","last_reissued_at":"2026-07-05T08:34:14.679841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:14.679841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marek Cygan, Mateusz Ostaszewski, Micha{\\l} Bortkiewicz, Michal Nauman, Piotr Mi{\\l}o\\'s, Tomasz Trzci\\'nski","submitted_at":"2024-03-01T13:25:10Z","abstract_excerpt":"Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional agents. However, many of these techniques have been tested in limited settings, often on tasks from single simulation benchmarks and against well-known algorithms rather than a range of regularization approaches. This limits our understanding of the specific mechanisms driving RL improvements. To address this, we implemented over 60 different off-policy agents, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00514","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/2403.00514/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":"2403.00514","created_at":"2026-07-05T08:34:14.679910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00514v2","created_at":"2026-07-05T08:34:14.679910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00514","created_at":"2026-07-05T08:34:14.679910+00:00"},{"alias_kind":"pith_short_12","alias_value":"F22XKRM75OGK","created_at":"2026-07-05T08:34:14.679910+00:00"},{"alias_kind":"pith_short_16","alias_value":"F22XKRM75OGKA4GE","created_at":"2026-07-05T08:34:14.679910+00:00"},{"alias_kind":"pith_short_8","alias_value":"F22XKRM7","created_at":"2026-07-05T08:34:14.679910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22562","citing_title":"Activation Function Design Sustains Plasticity in Continual Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01131","citing_title":"Forager: a lightweight testbed for continual learning with partial observability in RL","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML","json":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML.json","graph_json":"https://pith.science/api/pith-number/F22XKRM75OGKA4GEKJVEEP7CML/graph.json","events_json":"https://pith.science/api/pith-number/F22XKRM75OGKA4GEKJVEEP7CML/events.json","paper":"https://pith.science/paper/F22XKRM7"},"agent_actions":{"view_html":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML","download_json":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML.json","view_paper":"https://pith.science/paper/F22XKRM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00514&json=true","fetch_graph":"https://pith.science/api/pith-number/F22XKRM75OGKA4GEKJVEEP7CML/graph.json","fetch_events":"https://pith.science/api/pith-number/F22XKRM75OGKA4GEKJVEEP7CML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML/action/storage_attestation","attest_author":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML/action/author_attestation","sign_citation":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML/action/citation_signature","submit_replication":"https://pith.science/pith/F22XKRM75OGKA4GEKJVEEP7CML/action/replication_record"}},"created_at":"2026-07-05T08:34:14.679910+00:00","updated_at":"2026-07-05T08:34:14.679910+00:00"}