{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6E7ZMDYDK775ITJCVSSRVMOQQI","short_pith_number":"pith:6E7ZMDYD","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"},"canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","source":{"kind":"arxiv","id":"1905.05380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05380","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05380v1","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05380","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"6E7ZMDYDK775","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6E7ZMDYDK775ITJC","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6E7ZMDYD","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6E7ZMDYDK775ITJCVSSRVMOQQI","target":"record","payload":{"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"},"canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","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"},"source_kind":"arxiv","source_id":"1905.05380","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":"2026-05-17T23:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiNPABP+Ud0ufuGvFSbkyJbYckktKV78BUi39lIFIV2BHzu0IPHCFCvYdfdXyCMTy/QsWfR0l8UaOp4AmeH8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:34:30.957350Z"},"content_sha256":"e3d9bebe8ebb7c6dcf117b68fa0d8f95faf1392b193824c0b0dc2792a9397028","schema_version":"1.0","event_id":"sha256:e3d9bebe8ebb7c6dcf117b68fa0d8f95faf1392b193824c0b0dc2792a9397028"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6E7ZMDYDK775ITJCVSSRVMOQQI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyahau1jVpUBUPPG89SCU2n9rn4+OXS3EJU+fDNbIDY0zDfH6jNPdW/0QEDoZO8X3ZJRnAIGReNw0Bqrov9rBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:34:30.958033Z"},"content_sha256":"0e75436a368a115176f18a79784c99f430d4e4e9e12f72813fca4417be21ea6c","schema_version":"1.0","event_id":"sha256:0e75436a368a115176f18a79784c99f430d4e4e9e12f72813fca4417be21ea6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/bundle.json","state_url":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/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":"2026-05-26T13:34:30Z","links":{"resolver":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI","bundle":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/bundle.json","state":"https://pith.science/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6E7ZMDYDK775ITJCVSSRVMOQQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6E7ZMDYDK775ITJCVSSRVMOQQI","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":"17d0b88d07da35904509e3ff4206656405ea16b4e908db8d1950c5425d556696","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T03:37:37Z","title_canon_sha256":"53b6d2e5cf6512d720ad6e8cade1e8c4e0e97ae3611a7c7ca5128893338be77f"},"schema_version":"1.0","source":{"id":"1905.05380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05380","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05380v1","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05380","created_at":"2026-05-17T23:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"6E7ZMDYDK775","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6E7ZMDYDK775ITJC","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6E7ZMDYD","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:0e75436a368a115176f18a79784c99f430d4e4e9e12f72813fca4417be21ea6c","target":"graph","created_at":"2026-05-17T23:46:16Z","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"},"paper":{"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 ","authors_text":"Abhinav Verma, Gabor Orosz, Joel W. Burdick, Richard Cheng, Swarat Chaudhuri, Yisong Yue","cross_cats":["cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T03:37:37Z","title":"Control Regularization for Reduced Variance Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05380","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:e3d9bebe8ebb7c6dcf117b68fa0d8f95faf1392b193824c0b0dc2792a9397028","target":"record","created_at":"2026-05-17T23:46:16Z","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":"17d0b88d07da35904509e3ff4206656405ea16b4e908db8d1950c5425d556696","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T03:37:37Z","title_canon_sha256":"53b6d2e5cf6512d720ad6e8cade1e8c4e0e97ae3611a7c7ca5128893338be77f"},"schema_version":"1.0","source":{"id":"1905.05380","kind":"arxiv","version":1}},"canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f13f960f0357ffd44d22aca51ab1d08229e6fb4f6e46f892e7cdb2c4e5dce4f0","first_computed_at":"2026-05-17T23:46:16.684181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:16.684181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fifew067PHSdaTyZ3XPbFrECBBGjaiwqSxnV5F1A+tRX/BKKBdqF1128FxujkLYdQaFTqj2jrFE5fhF90VVsAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:16.684788Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3d9bebe8ebb7c6dcf117b68fa0d8f95faf1392b193824c0b0dc2792a9397028","sha256:0e75436a368a115176f18a79784c99f430d4e4e9e12f72813fca4417be21ea6c"],"state_sha256":"8b153f2bf00caf5a24a2ebdf2d82f49a73b5ae1b7686c8a280a3f4321f40f9e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"elI1/FAuYkO4Ij3UURgi2AuIZYx2ES55QrlnUgaXoJGcufQ/af9ZlWUG6b+cWYx0AITv+9cGb2fdWIuU/9uACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:34:30.961464Z","bundle_sha256":"0459430b249c12eb78b3b92b7092340aad529f3630ffb5d20e9ff3da42aa6489"}}