{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FOPBVGU2W6HW75Y3TFTGLLVY2J","short_pith_number":"pith:FOPBVGU2","canonical_record":{"source":{"id":"1712.02037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-06T04:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"2476843d0704f2c5f59e404f693034d85fb9ed747842b9d71a1e9ff1cb7dabd9","abstract_canon_sha256":"506ae32c33beb92d0f1bb6cd6ddbdc966a5165c3f50c0711faa03ee47e81a9f3"},"schema_version":"1.0"},"canonical_sha256":"2b9e1a9a9ab78f6ff71b996665aeb8d27fd73561fb783b93440bbfbf8e73ed96","source":{"kind":"arxiv","id":"1712.02037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.02037","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"1712.02037v1","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02037","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"FOPBVGU2W6HW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FOPBVGU2W6HW75Y3","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FOPBVGU2","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FOPBVGU2W6HW75Y3TFTGLLVY2J","target":"record","payload":{"canonical_record":{"source":{"id":"1712.02037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-06T04:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"2476843d0704f2c5f59e404f693034d85fb9ed747842b9d71a1e9ff1cb7dabd9","abstract_canon_sha256":"506ae32c33beb92d0f1bb6cd6ddbdc966a5165c3f50c0711faa03ee47e81a9f3"},"schema_version":"1.0"},"canonical_sha256":"2b9e1a9a9ab78f6ff71b996665aeb8d27fd73561fb783b93440bbfbf8e73ed96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:39.385577Z","signature_b64":"2e/0QUhgCpT/hEJrmHBoquj5T8Pr2+Bg8hB+8ldzDYb8r2/ygkTLzjA+bdI9dAC20LBLh5Thycu11RSn2qTwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b9e1a9a9ab78f6ff71b996665aeb8d27fd73561fb783b93440bbfbf8e73ed96","last_reissued_at":"2026-05-18T00:28:39.384890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:39.384890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.02037","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":"2026-05-18T00:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kG7mHk8zMVvrakJWM7WSOP11+DYaj2IoK+KXjq1YPL6QNoLg/3XnJWH8JSiFMcIUliuZEJ+r2wkXUNzR42gSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T22:48:50.435097Z"},"content_sha256":"00bacf2ad7c258db9c7eba551b903cdf8a707ad8941267d75f9ce246aee64c27","schema_version":"1.0","event_id":"sha256:00bacf2ad7c258db9c7eba551b903cdf8a707ad8941267d75f9ce246aee64c27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FOPBVGU2W6HW75Y3TFTGLLVY2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Policy Gradients via Alpha Divergence Dropout Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Meger, Peter Henderson, Riashat Islam, Thang Doan","submitted_at":"2017-12-06T04:38:06Z","abstract_excerpt":"Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by fitting the value function with a Bayesian Neural Network. We optimize an $\\alpha$-divergence objective with Bayesian dropout approximation to learn and estimate this distribution. We show that using the Monte Carlo posterior mean of the Bayesian value function distribution, rather than a deterministic network, improves stability and performance of policy gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02037","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":"2026-05-18T00:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/n+F8Q7U3Jj6kvtSK+ZqFyYRCyETXU8GRKK0tTrX2cwg1NaToebr4jtgHQ1VZHPUhC42AokSxU1ngLF7DXV8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T22:48:50.435815Z"},"content_sha256":"36a98a8d9a050076b3f7d29d18ca8e3412a2b926bc4969719573fa8b2dea3ddd","schema_version":"1.0","event_id":"sha256:36a98a8d9a050076b3f7d29d18ca8e3412a2b926bc4969719573fa8b2dea3ddd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/bundle.json","state_url":"https://pith.science/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/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":"2026-06-07T22:48:50Z","links":{"resolver":"https://pith.science/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J","bundle":"https://pith.science/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/bundle.json","state":"https://pith.science/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FOPBVGU2W6HW75Y3TFTGLLVY2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FOPBVGU2W6HW75Y3TFTGLLVY2J","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":"506ae32c33beb92d0f1bb6cd6ddbdc966a5165c3f50c0711faa03ee47e81a9f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-06T04:38:06Z","title_canon_sha256":"2476843d0704f2c5f59e404f693034d85fb9ed747842b9d71a1e9ff1cb7dabd9"},"schema_version":"1.0","source":{"id":"1712.02037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.02037","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"1712.02037v1","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02037","created_at":"2026-05-18T00:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"FOPBVGU2W6HW","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FOPBVGU2W6HW75Y3","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FOPBVGU2","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:36a98a8d9a050076b3f7d29d18ca8e3412a2b926bc4969719573fa8b2dea3ddd","target":"graph","created_at":"2026-05-18T00:28:39Z","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":"Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by fitting the value function with a Bayesian Neural Network. We optimize an $\\alpha$-divergence objective with Bayesian dropout approximation to learn and estimate this distribution. We show that using the Monte Carlo posterior mean of the Bayesian value function distribution, rather than a deterministic network, improves stability and performance of policy gr","authors_text":"David Meger, Peter Henderson, Riashat Islam, Thang Doan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-06T04:38:06Z","title":"Bayesian Policy Gradients via Alpha Divergence Dropout Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02037","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":"sha256:00bacf2ad7c258db9c7eba551b903cdf8a707ad8941267d75f9ce246aee64c27","target":"record","created_at":"2026-05-18T00:28:39Z","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":"506ae32c33beb92d0f1bb6cd6ddbdc966a5165c3f50c0711faa03ee47e81a9f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-06T04:38:06Z","title_canon_sha256":"2476843d0704f2c5f59e404f693034d85fb9ed747842b9d71a1e9ff1cb7dabd9"},"schema_version":"1.0","source":{"id":"1712.02037","kind":"arxiv","version":1}},"canonical_sha256":"2b9e1a9a9ab78f6ff71b996665aeb8d27fd73561fb783b93440bbfbf8e73ed96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b9e1a9a9ab78f6ff71b996665aeb8d27fd73561fb783b93440bbfbf8e73ed96","first_computed_at":"2026-05-18T00:28:39.384890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:39.384890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2e/0QUhgCpT/hEJrmHBoquj5T8Pr2+Bg8hB+8ldzDYb8r2/ygkTLzjA+bdI9dAC20LBLh5Thycu11RSn2qTwBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:39.385577Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.02037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00bacf2ad7c258db9c7eba551b903cdf8a707ad8941267d75f9ce246aee64c27","sha256:36a98a8d9a050076b3f7d29d18ca8e3412a2b926bc4969719573fa8b2dea3ddd"],"state_sha256":"b68ad900fdd2b56d4e794f4235bae70a322855fd1893136bc79647ef46ce0658"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QsmTZjxVxzmiw2S9Y8jy8pwpdkj7GWFpaAdi9ZIvyBq5MO6RYuLkRffcIaemSkK6isHVTFyynegucwz0gNeCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T22:48:50.439600Z","bundle_sha256":"75ab074b5accf80f219c6b5526505f8efb88de20b84a1d8a4edde37a88a483b0"}}