{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3ZX2NHCZOCZ5IHR3T5RLYJXYBR","short_pith_number":"pith:3ZX2NHCZ","schema_version":"1.0","canonical_sha256":"de6fa69c5970b3d41e3b9f62bc26f80c57cb5e6a76faab5f566727032461682a","source":{"kind":"arxiv","id":"1910.09191","version":5},"attestation_state":"computed","paper":{"title":"Regularization Matters in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Trevor Darrell, Xuanlin Li, Zhuang Liu","submitted_at":"2019-10-21T08:00:33Z","abstract_excerpt":"Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$ regularization, dropout) have been largely ignored in RL methods, possibly because agents are typically trained and evaluated in the same environment, and because the deep RL community focuses more on high-level algorithm designs. In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms o"},"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":"1910.09191","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-21T08:00:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ee09e119952e05cb7b83be9de992735ecb31c85cf4eb69ed60148f49ce527030","abstract_canon_sha256":"f2b37ff7c481157ca3e6e8f01a108f77d7b075bfd4dc70755ad3890d97e0de71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:24.945758Z","signature_b64":"PdZqSRMMXLlOahDr49uybUT/zV2cSiwxVJjQGxQOCN5/X5k2YWNdVjB1hO/PbKARurm8jeZG699ci3IWRGAGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6fa69c5970b3d41e3b9f62bc26f80c57cb5e6a76faab5f566727032461682a","last_reissued_at":"2026-07-05T03:35:24.945268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:24.945268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularization Matters in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Trevor Darrell, Xuanlin Li, Zhuang Liu","submitted_at":"2019-10-21T08:00:33Z","abstract_excerpt":"Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$ regularization, dropout) have been largely ignored in RL methods, possibly because agents are typically trained and evaluated in the same environment, and because the deep RL community focuses more on high-level algorithm designs. In this work, we present the first comprehensive study of regularization techniques with multiple policy optimization algorithms o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09191","kind":"arxiv","version":5},"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/1910.09191/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":"1910.09191","created_at":"2026-07-05T03:35:24.945331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09191v5","created_at":"2026-07-05T03:35:24.945331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09191","created_at":"2026-07-05T03:35:24.945331+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZX2NHCZOCZ5","created_at":"2026-07-05T03:35:24.945331+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZX2NHCZOCZ5IHR3","created_at":"2026-07-05T03:35:24.945331+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZX2NHCZ","created_at":"2026-07-05T03:35:24.945331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13875","citing_title":"Common-agency Games for Multi-Objective Test-Time Alignment","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09214","citing_title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02112","citing_title":"An adaptive variance estimator for relative sparsity","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR","json":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR.json","graph_json":"https://pith.science/api/pith-number/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/graph.json","events_json":"https://pith.science/api/pith-number/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/events.json","paper":"https://pith.science/paper/3ZX2NHCZ"},"agent_actions":{"view_html":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR","download_json":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR.json","view_paper":"https://pith.science/paper/3ZX2NHCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09191&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/action/storage_attestation","attest_author":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/action/author_attestation","sign_citation":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/action/citation_signature","submit_replication":"https://pith.science/pith/3ZX2NHCZOCZ5IHR3T5RLYJXYBR/action/replication_record"}},"created_at":"2026-07-05T03:35:24.945331+00:00","updated_at":"2026-07-05T03:35:24.945331+00:00"}