{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6E7ZMDYDK775ITJCVSSRVMOQQI","short_pith_number":"pith:6E7ZMDYD","schema_version":"1.0","canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","source":{"kind":"arxiv","id":"1905.05380","version":1},"attestation_state":"computed","paper":{"title":"Control Regularization for Reduced Variance Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Gabor Orosz, Joel W. Burdick, Richard Cheng, Swarat Chaudhuri, Yisong Yue","submitted_at":"2019-05-14T03:37:37Z","abstract_excerpt":"Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a policy prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy "},"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":"1905.05380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T03:37:37Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"53b6d2e5cf6512d720ad6e8cade1e8c4e0e97ae3611a7c7ca5128893338be77f","abstract_canon_sha256":"17d0b88d07da35904509e3ff4206656405ea16b4e908db8d1950c5425d556696"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:16.684788Z","signature_b64":"fifew067PHSdaTyZ3XPbFrECBBGjaiwqSxnV5F1A+tRX/BKKBdqF1128FxujkLYdQaFTqj2jrFE5fhF90VVsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","last_reissued_at":"2026-05-17T23:46:16.684181Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:16.684181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control Regularization for Reduced Variance Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Gabor Orosz, Joel W. Burdick, Richard Cheng, Swarat Chaudhuri, Yisong Yue","submitted_at":"2019-05-14T03:37:37Z","abstract_excerpt":"Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a policy prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05380","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.05380","created_at":"2026-05-17T23:46:16.684275+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05380v1","created_at":"2026-05-17T23:46:16.684275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05380","created_at":"2026-05-17T23:46:16.684275+00:00"},{"alias_kind":"pith_short_12","alias_value":"6E7ZMDYDK775","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6E7ZMDYDK775ITJC","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6E7ZMDYD","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI","json":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI.json","graph_json":"https://pith.science/api/pith-number/6E7ZMDYDK775ITJCVSSRVMOQQI/graph.json","events_json":"https://pith.science/api/pith-number/6E7ZMDYDK775ITJCVSSRVMOQQI/events.json","paper":"https://pith.science/paper/6E7ZMDYD"},"agent_actions":{"view_html":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI","download_json":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI.json","view_paper":"https://pith.science/paper/6E7ZMDYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05380&json=true","fetch_graph":"https://pith.science/api/pith-number/6E7ZMDYDK775ITJCVSSRVMOQQI/graph.json","fetch_events":"https://pith.science/api/pith-number/6E7ZMDYDK775ITJCVSSRVMOQQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/action/storage_attestation","attest_author":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/action/author_attestation","sign_citation":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/action/citation_signature","submit_replication":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/action/replication_record"}},"created_at":"2026-05-17T23:46:16.684275+00:00","updated_at":"2026-05-17T23:46:16.684275+00:00"}