{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JQ66HOKDHB7UAJJZKGO45SIKS2","short_pith_number":"pith:JQ66HOKD","canonical_record":{"source":{"id":"1911.11640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-11-26T15:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"94b5ecd3286466ec80e3ad2394acc3c7f8c5391c6db82f62313a142f8bfaae78","abstract_canon_sha256":"9943913cb2ce1e7d858fe8e3a1b02c8f0f85a240049785960980e59092c4216b"},"schema_version":"1.0"},"canonical_sha256":"4c3de3b943387f402539519dcec90a96b4ea816a975a0df4fb616bbda02ac263","source":{"kind":"arxiv","id":"1911.11640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11640","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11640v1","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11640","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"JQ66HOKDHB7U","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"JQ66HOKDHB7UAJJZ","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"JQ66HOKD","created_at":"2026-07-05T00:22:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JQ66HOKDHB7UAJJZKGO45SIKS2","target":"record","payload":{"canonical_record":{"source":{"id":"1911.11640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-11-26T15:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"94b5ecd3286466ec80e3ad2394acc3c7f8c5391c6db82f62313a142f8bfaae78","abstract_canon_sha256":"9943913cb2ce1e7d858fe8e3a1b02c8f0f85a240049785960980e59092c4216b"},"schema_version":"1.0"},"canonical_sha256":"4c3de3b943387f402539519dcec90a96b4ea816a975a0df4fb616bbda02ac263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:11.930844Z","signature_b64":"HE9DqDkc/bZwVcpFHZq+lNe3Yfige5Ph8eQl8UPO7Ru4/rwOc2J+8jBqpOShjW0BC+DGEts8q/8QT41F6UTyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c3de3b943387f402539519dcec90a96b4ea816a975a0df4fb616bbda02ac263","last_reissued_at":"2026-07-05T00:22:11.930354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:11.930354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.11640","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":"2026-07-05T00:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTJm31zIJrAFtetjPCR6XXU3Dl8weectnb8rUVFbXNqBz5ZqFM6Gupd2Qej+7zeKulOQ7OTROnA/Q1imHRv4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:15:40.794787Z"},"content_sha256":"42a4dac9e3100f997d07af76d6ba1c18e32c00e3ed51a651444c870b8c2bb13f","schema_version":"1.0","event_id":"sha256:42a4dac9e3100f997d07af76d6ba1c18e32c00e3ed51a651444c870b8c2bb13f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JQ66HOKDHB7UAJJZKGO45SIKS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Stochastic Trust-Region Framework for Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Mingming Zhao, Yongfeng Li, Zaiwen Wen","submitted_at":"2019-11-26T15:27:13Z","abstract_excerpt":"In this paper, we study a few challenging theoretical and numerical issues on the well known trust region policy optimization for deep reinforcement learning. The goal is to find a policy that maximizes the total expected reward when the agent acts according to the policy. The trust region subproblem is constructed with a surrogate function coherent to the total expected reward and a general distance constraint around the latest policy. We solve the subproblem using a preconditioned stochastic gradient method with a line search scheme to ensure that each step promotes the model function and st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11640","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.11640/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BD6rQ6OQ2TZnpO0imHsCZVJrIZzbg3t9lj8vuBZNejqyZdM9cM3YcNJclBZggaBj5u+XTQF1BB0kt01kgTHJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:15:40.795943Z"},"content_sha256":"25363643b0096cddc855481ee562dd4bc98f9f5fe61063cd8dd91cca69424d57","schema_version":"1.0","event_id":"sha256:25363643b0096cddc855481ee562dd4bc98f9f5fe61063cd8dd91cca69424d57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/bundle.json","state_url":"https://pith.science/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/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":"2026-08-15T17:15:40Z","links":{"resolver":"https://pith.science/pith/JQ66HOKDHB7UAJJZKGO45SIKS2","bundle":"https://pith.science/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/bundle.json","state":"https://pith.science/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQ66HOKDHB7UAJJZKGO45SIKS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JQ66HOKDHB7UAJJZKGO45SIKS2","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":"9943913cb2ce1e7d858fe8e3a1b02c8f0f85a240049785960980e59092c4216b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-11-26T15:27:13Z","title_canon_sha256":"94b5ecd3286466ec80e3ad2394acc3c7f8c5391c6db82f62313a142f8bfaae78"},"schema_version":"1.0","source":{"id":"1911.11640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11640","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11640v1","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11640","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"JQ66HOKDHB7U","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"JQ66HOKDHB7UAJJZ","created_at":"2026-07-05T00:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"JQ66HOKD","created_at":"2026-07-05T00:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:25363643b0096cddc855481ee562dd4bc98f9f5fe61063cd8dd91cca69424d57","target":"graph","created_at":"2026-07-05T00:22:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.11640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study a few challenging theoretical and numerical issues on the well known trust region policy optimization for deep reinforcement learning. The goal is to find a policy that maximizes the total expected reward when the agent acts according to the policy. The trust region subproblem is constructed with a surrogate function coherent to the total expected reward and a general distance constraint around the latest policy. We solve the subproblem using a preconditioned stochastic gradient method with a line search scheme to ensure that each step promotes the model function and st","authors_text":"Mingming Zhao, Yongfeng Li, Zaiwen Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-11-26T15:27:13Z","title":"A Stochastic Trust-Region Framework for Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11640","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":"sha256:42a4dac9e3100f997d07af76d6ba1c18e32c00e3ed51a651444c870b8c2bb13f","target":"record","created_at":"2026-07-05T00:22:11Z","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":"9943913cb2ce1e7d858fe8e3a1b02c8f0f85a240049785960980e59092c4216b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-11-26T15:27:13Z","title_canon_sha256":"94b5ecd3286466ec80e3ad2394acc3c7f8c5391c6db82f62313a142f8bfaae78"},"schema_version":"1.0","source":{"id":"1911.11640","kind":"arxiv","version":1}},"canonical_sha256":"4c3de3b943387f402539519dcec90a96b4ea816a975a0df4fb616bbda02ac263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c3de3b943387f402539519dcec90a96b4ea816a975a0df4fb616bbda02ac263","first_computed_at":"2026-07-05T00:22:11.930354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:22:11.930354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HE9DqDkc/bZwVcpFHZq+lNe3Yfige5Ph8eQl8UPO7Ru4/rwOc2J+8jBqpOShjW0BC+DGEts8q/8QT41F6UTyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:22:11.930844Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.11640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42a4dac9e3100f997d07af76d6ba1c18e32c00e3ed51a651444c870b8c2bb13f","sha256:25363643b0096cddc855481ee562dd4bc98f9f5fe61063cd8dd91cca69424d57"],"state_sha256":"8172f14f8cd20a3767a21f45ba276331d8c9814cad506f8f413d3296bae6e8cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBLh9bdz8nyW/5EceEjm87eVxt4w8/fC1Fk/Rq1U1YC9wLkLIQ95j31vVxB6EmNe9TcrZaUq3o3Xlk5GSi1RBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:15:40.800470Z","bundle_sha256":"010b56afdef31bc2250557572e39134e164f74c6d38a3944fc93a488e7c5cb42"}}