{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4AKPFK2QHD3LKOKKBSJAT4HOAO","short_pith_number":"pith:4AKPFK2Q","canonical_record":{"source":{"id":"1902.03633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-10T17:18:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"32069e2f1c09452344773f44d40104d9e049704843eb04728011a28334173196","abstract_canon_sha256":"751bd5989aaad75fa2ea557d9fd0ba38538b33ec8803490247ddfc3a685d4a09"},"schema_version":"1.0"},"canonical_sha256":"e014f2ab5038f6b5394a0c9209f0ee038fe94a14e2c8f4bdf8cbb0deffc679b0","source":{"kind":"arxiv","id":"1902.03633","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03633","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03633v1","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03633","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"4AKPFK2QHD3L","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4AKPFK2QHD3LKOKK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4AKPFK2Q","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4AKPFK2QHD3LKOKKBSJAT4HOAO","target":"record","payload":{"canonical_record":{"source":{"id":"1902.03633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-10T17:18:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"32069e2f1c09452344773f44d40104d9e049704843eb04728011a28334173196","abstract_canon_sha256":"751bd5989aaad75fa2ea557d9fd0ba38538b33ec8803490247ddfc3a685d4a09"},"schema_version":"1.0"},"canonical_sha256":"e014f2ab5038f6b5394a0c9209f0ee038fe94a14e2c8f4bdf8cbb0deffc679b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:20.128224Z","signature_b64":"esJ/1906yvgvr68lcN5ZoAXbdIF1dZYb2DXoyUQbMVD0Dsjvic47y1IiwyZlThR1CpjEqCYOupkqaWFber4NDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e014f2ab5038f6b5394a0c9209f0ee038fe94a14e2c8f4bdf8cbb0deffc679b0","last_reissued_at":"2026-05-17T23:54:20.127580Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:20.127580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.03633","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":"2026-05-17T23:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YeGjwW+8ad8cUhZRUVLPhwq+npbaBK+iIY5G1M4yDjgVZcf9/NQxPycNtBs7NueFCKv7/cTHoP4YxyA60T1UDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:14:44.167677Z"},"content_sha256":"5d2a61001019f6852408c8a878ad2b13c0c002d9015ec974f82b447b000218b2","schema_version":"1.0","event_id":"sha256:5d2a61001019f6852408c8a878ad2b13c0c002d9015ec974f82b447b000218b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4AKPFK2QHD3LKOKKBSJAT4HOAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Exploration via Conjugate Policies for Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Cohen, Elliot Way, Lei Yu, Xiangrong Tong, Xingye Qiao","submitted_at":"2019-02-10T17:18:49Z","abstract_excerpt":"We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of conjugate policies which can be conveniently generated as a byproduct of conjugate gradient descent. We provide both theoretical and empirical results showing the effectiveness of DE at achieving exploration, improving policy performance, and the advantage of DE over exploration by random policy perturbations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03633","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":"2026-05-17T23:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G8tq0cSzVFI3Dzj7imbsdcYEZy+cfZxWK5DajRFIHzkTWZ5z5X+LaTcU9g+MNku94sVuWEkn5aOxmR8Q9/BoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:14:44.168020Z"},"content_sha256":"9b9a37e884a640c7a632529a1463a836d479b25d958c1b099c405bd2644fab3d","schema_version":"1.0","event_id":"sha256:9b9a37e884a640c7a632529a1463a836d479b25d958c1b099c405bd2644fab3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/bundle.json","state_url":"https://pith.science/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/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":"2026-06-02T03:14:44Z","links":{"resolver":"https://pith.science/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO","bundle":"https://pith.science/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/bundle.json","state":"https://pith.science/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AKPFK2QHD3LKOKKBSJAT4HOAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4AKPFK2QHD3LKOKKBSJAT4HOAO","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":"751bd5989aaad75fa2ea557d9fd0ba38538b33ec8803490247ddfc3a685d4a09","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-10T17:18:49Z","title_canon_sha256":"32069e2f1c09452344773f44d40104d9e049704843eb04728011a28334173196"},"schema_version":"1.0","source":{"id":"1902.03633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03633","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03633v1","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03633","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"4AKPFK2QHD3L","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4AKPFK2QHD3LKOKK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4AKPFK2Q","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:9b9a37e884a640c7a632529a1463a836d479b25d958c1b099c405bd2644fab3d","target":"graph","created_at":"2026-05-17T23:54:20Z","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":"We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of conjugate policies which can be conveniently generated as a byproduct of conjugate gradient descent. We provide both theoretical and empirical results showing the effectiveness of DE at achieving exploration, improving policy performance, and the advantage of DE over exploration by random policy perturbations.","authors_text":"Andrew Cohen, Elliot Way, Lei Yu, Xiangrong Tong, Xingye Qiao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-10T17:18:49Z","title":"Diverse Exploration via Conjugate Policies for Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03633","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":"sha256:5d2a61001019f6852408c8a878ad2b13c0c002d9015ec974f82b447b000218b2","target":"record","created_at":"2026-05-17T23:54:20Z","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":"751bd5989aaad75fa2ea557d9fd0ba38538b33ec8803490247ddfc3a685d4a09","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-10T17:18:49Z","title_canon_sha256":"32069e2f1c09452344773f44d40104d9e049704843eb04728011a28334173196"},"schema_version":"1.0","source":{"id":"1902.03633","kind":"arxiv","version":1}},"canonical_sha256":"e014f2ab5038f6b5394a0c9209f0ee038fe94a14e2c8f4bdf8cbb0deffc679b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e014f2ab5038f6b5394a0c9209f0ee038fe94a14e2c8f4bdf8cbb0deffc679b0","first_computed_at":"2026-05-17T23:54:20.127580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:20.127580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"esJ/1906yvgvr68lcN5ZoAXbdIF1dZYb2DXoyUQbMVD0Dsjvic47y1IiwyZlThR1CpjEqCYOupkqaWFber4NDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:20.128224Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.03633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d2a61001019f6852408c8a878ad2b13c0c002d9015ec974f82b447b000218b2","sha256:9b9a37e884a640c7a632529a1463a836d479b25d958c1b099c405bd2644fab3d"],"state_sha256":"c3a5e57aff3f9c23b3127aaf27fb428e508b73a359a44e44ff2f78e344b9836a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"heGXNsfjOWikp2O1PsoOZdeaJY7GW0ATwZPDOwT+SBE8cIJQoUH1y1kZ2kPDYOc6iYLy0une6VYIYoxP8nZMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T03:14:44.170056Z","bundle_sha256":"9a6500ce6f72da830b6702fd1a503af9fb4ecc339cb95a66bd1f90a10f519a63"}}