{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:IVQEY3YUYJZL2EHSQA6L3FW6SJ","short_pith_number":"pith:IVQEY3YU","canonical_record":{"source":{"id":"1502.05477","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"b60dc0f59dcb0084c59dd62e514ae98c5367cb138d520229a2682bc708634d40","abstract_canon_sha256":"b40778b0e01a0bac6fc7f67f1bb23ef7affec61a5861fec6cbf8679733aa488f"},"schema_version":"1.0"},"canonical_sha256":"45604c6f14c272bd10f2803cbd96de926b87a9f7c1f66482425cc4a82f8d5a2f","source":{"kind":"arxiv","id":"1502.05477","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05477","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05477v5","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05477","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"IVQEY3YUYJZL","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IVQEY3YUYJZL2EHS","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IVQEY3YU","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:IVQEY3YUYJZL2EHSQA6L3FW6SJ","target":"record","payload":{"canonical_record":{"source":{"id":"1502.05477","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"b60dc0f59dcb0084c59dd62e514ae98c5367cb138d520229a2682bc708634d40","abstract_canon_sha256":"b40778b0e01a0bac6fc7f67f1bb23ef7affec61a5861fec6cbf8679733aa488f"},"schema_version":"1.0"},"canonical_sha256":"45604c6f14c272bd10f2803cbd96de926b87a9f7c1f66482425cc4a82f8d5a2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:02.905473Z","signature_b64":"2tQ6bbFP+b2d4mPFeM6ayWN88Oi1cQrcw/yvrXYfue603cX6ti4SARHPfYx0YYiMX3iY+l3FCWV8l+7xdVH1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45604c6f14c272bd10f2803cbd96de926b87a9f7c1f66482425cc4a82f8d5a2f","last_reissued_at":"2026-05-18T00:46:02.904977Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:02.904977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.05477","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s53iG7WgEEOOLAr4xgE9QPz072d++8Ws0Y422wz5FbheeHGqnLCVMYrLd7GOkl2L82moc8voGl3r6mf6xc0kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:38:17.007525Z"},"content_sha256":"8110656b5a9de2d8c0e2a3c0e30497597c21a80d2adfaff2494d4186e117eb65","schema_version":"1.0","event_id":"sha256:8110656b5a9de2d8c0e2a3c0e30497597c21a80d2adfaff2494d4186e117eb65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:IVQEY3YUYJZL2EHSQA6L3FW6SJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust Region Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"John Schulman, Michael I. Jordan, Philipp Moritz, Pieter Abbeel, Sergey Levine","submitted_at":"2015-02-19T06:44:25Z","abstract_excerpt":"We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is similar to natural policy gradient methods and is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05477","kind":"arxiv","version":5},"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":"2026-05-18T00:46:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfIQxjsoVr0N6+T6dLOtA5nlD9SoHoHvVJdvc6vtpEIxNj7HoxoUMmijGMiWMTo5F+K8c4ZGPdBgDpQUmhPlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:38:17.007872Z"},"content_sha256":"ef4cb7584b3c03c4c01472b5d92f17042bb256dbad6a601531ed14b3fe173706","schema_version":"1.0","event_id":"sha256:ef4cb7584b3c03c4c01472b5d92f17042bb256dbad6a601531ed14b3fe173706"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/bundle.json","state_url":"https://pith.science/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/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":"2026-06-03T00:38:17Z","links":{"resolver":"https://pith.science/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ","bundle":"https://pith.science/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/bundle.json","state":"https://pith.science/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVQEY3YUYJZL2EHSQA6L3FW6SJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:IVQEY3YUYJZL2EHSQA6L3FW6SJ","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":"b40778b0e01a0bac6fc7f67f1bb23ef7affec61a5861fec6cbf8679733aa488f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:44:25Z","title_canon_sha256":"b60dc0f59dcb0084c59dd62e514ae98c5367cb138d520229a2682bc708634d40"},"schema_version":"1.0","source":{"id":"1502.05477","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.05477","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"1502.05477v5","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.05477","created_at":"2026-05-18T00:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"IVQEY3YUYJZL","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IVQEY3YUYJZL2EHS","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IVQEY3YU","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:ef4cb7584b3c03c4c01472b5d92f17042bb256dbad6a601531ed14b3fe173706","target":"graph","created_at":"2026-05-18T00:46:02Z","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 describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is similar to natural policy gradient methods and is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate its robust performance on a wide variety of tasks: learning simulated robotic swimming, hopping, and walking gaits; and playing Atari games using images of the screen as inp","authors_text":"John Schulman, Michael I. Jordan, Philipp Moritz, Pieter Abbeel, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:44:25Z","title":"Trust Region Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.05477","kind":"arxiv","version":5},"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":"sha256:8110656b5a9de2d8c0e2a3c0e30497597c21a80d2adfaff2494d4186e117eb65","target":"record","created_at":"2026-05-18T00:46:02Z","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":"b40778b0e01a0bac6fc7f67f1bb23ef7affec61a5861fec6cbf8679733aa488f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-19T06:44:25Z","title_canon_sha256":"b60dc0f59dcb0084c59dd62e514ae98c5367cb138d520229a2682bc708634d40"},"schema_version":"1.0","source":{"id":"1502.05477","kind":"arxiv","version":5}},"canonical_sha256":"45604c6f14c272bd10f2803cbd96de926b87a9f7c1f66482425cc4a82f8d5a2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45604c6f14c272bd10f2803cbd96de926b87a9f7c1f66482425cc4a82f8d5a2f","first_computed_at":"2026-05-18T00:46:02.904977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:02.904977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2tQ6bbFP+b2d4mPFeM6ayWN88Oi1cQrcw/yvrXYfue603cX6ti4SARHPfYx0YYiMX3iY+l3FCWV8l+7xdVH1Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:02.905473Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.05477","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8110656b5a9de2d8c0e2a3c0e30497597c21a80d2adfaff2494d4186e117eb65","sha256:ef4cb7584b3c03c4c01472b5d92f17042bb256dbad6a601531ed14b3fe173706"],"state_sha256":"2c17c211985c1242ed102d278962f5c3d88d0051ecdeb80ecb4b3303e81f4976"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pKoDveaU1mvjGcPIm47nH3PR1uuAzd45Wuh5Wo2ozahztCL6uOyVp5iyWf5VVmGaOA4v7AXScWMv/uF2lZhdCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:38:17.009867Z","bundle_sha256":"c2c55ed30732969344d24826de710c27e7486e9b55a06c4e4d80fe987891e40e"}}