{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SG2TPGUPUWNNYI7GEXZ3LRPH4Q","short_pith_number":"pith:SG2TPGUP","canonical_record":{"source":{"id":"1805.08180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T17:02:53Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"baff8a8cfffef663deaf3d0800a942be7889857fa6c72805b81b965ea4e313f9","abstract_canon_sha256":"09dbaab3a164cde0fccaf8312156238f36c31da5750ed9a5e299d4bb6a2040a5"},"schema_version":"1.0"},"canonical_sha256":"91b5379a8fa59adc23e625f3b5c5e7e42f6ac13740b5110595fbaaf2a4887536","source":{"kind":"arxiv","id":"1805.08180","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08180","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08180v2","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08180","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"SG2TPGUPUWNN","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SG2TPGUPUWNNYI7G","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SG2TPGUP","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SG2TPGUPUWNNYI7GEXZ3LRPH4Q","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T17:02:53Z","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"baff8a8cfffef663deaf3d0800a942be7889857fa6c72805b81b965ea4e313f9","abstract_canon_sha256":"09dbaab3a164cde0fccaf8312156238f36c31da5750ed9a5e299d4bb6a2040a5"},"schema_version":"1.0"},"canonical_sha256":"91b5379a8fa59adc23e625f3b5c5e7e42f6ac13740b5110595fbaaf2a4887536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:49.397232Z","signature_b64":"FkcarH2Q0IIfd31EEF2MzD3kAW0p7b48xE10+fd2+56zecDr2QcIS7OuBoQ7aGyWRwsv5sX51xI6hilzk7sfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b5379a8fa59adc23e625f3b5c5e7e42f6ac13740b5110595fbaaf2a4887536","last_reissued_at":"2026-05-17T23:51:49.396603Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:49.396603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08180","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6iWc4vnXWkNW4r5bjQGH3yVrccOQ+S84Tuqf7fcJLhO7eDddjbjBAvnccObJ0bIkZZgULdHqHZhottCFT1zBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:47:17.137645Z"},"content_sha256":"79f84ad7c612b047cea5ad80f8573a7aa8f08aaf010c2f7004fe10a998929f20","schema_version":"1.0","event_id":"sha256:79f84ad7c612b047cea5ad80f8573a7aa8f08aaf010c2f7004fe10a998929f20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SG2TPGUPUWNNYI7GEXZ3LRPH4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning with Hindsight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Levy, Kate Saenko, Robert Platt","submitted_at":"2018-05-21T17:02:53Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08180","kind":"arxiv","version":2},"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":"2026-05-17T23:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8RNzI04/S2Gi+RSve5ZLBQrpA4o9eV0VNO7lqsICkw+QomcnGb/CCHg1GXl80sufTUWO9vYMde0hSv5LzuhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:47:17.138019Z"},"content_sha256":"4a3cfcc51a240eb1109f9e37c91ea1e146eef954cee6578377739c61ce5032bd","schema_version":"1.0","event_id":"sha256:4a3cfcc51a240eb1109f9e37c91ea1e146eef954cee6578377739c61ce5032bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/bundle.json","state_url":"https://pith.science/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/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":"2026-05-26T04:47:17Z","links":{"resolver":"https://pith.science/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q","bundle":"https://pith.science/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/bundle.json","state":"https://pith.science/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SG2TPGUPUWNNYI7GEXZ3LRPH4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SG2TPGUPUWNNYI7GEXZ3LRPH4Q","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":"09dbaab3a164cde0fccaf8312156238f36c31da5750ed9a5e299d4bb6a2040a5","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T17:02:53Z","title_canon_sha256":"baff8a8cfffef663deaf3d0800a942be7889857fa6c72805b81b965ea4e313f9"},"schema_version":"1.0","source":{"id":"1805.08180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08180","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08180v2","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08180","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"SG2TPGUPUWNN","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SG2TPGUPUWNNYI7G","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SG2TPGUP","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:4a3cfcc51a240eb1109f9e37c91ea1e146eef954cee6578377739c61ce5032bd","target":"graph","created_at":"2026-05-17T23:51:49Z","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":"Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.","authors_text":"Andrew Levy, Kate Saenko, Robert Platt","cross_cats":["cs.AI","cs.NE","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T17:02:53Z","title":"Hierarchical Reinforcement Learning with Hindsight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08180","kind":"arxiv","version":2},"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":"sha256:79f84ad7c612b047cea5ad80f8573a7aa8f08aaf010c2f7004fe10a998929f20","target":"record","created_at":"2026-05-17T23:51:49Z","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":"09dbaab3a164cde0fccaf8312156238f36c31da5750ed9a5e299d4bb6a2040a5","cross_cats_sorted":["cs.AI","cs.NE","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T17:02:53Z","title_canon_sha256":"baff8a8cfffef663deaf3d0800a942be7889857fa6c72805b81b965ea4e313f9"},"schema_version":"1.0","source":{"id":"1805.08180","kind":"arxiv","version":2}},"canonical_sha256":"91b5379a8fa59adc23e625f3b5c5e7e42f6ac13740b5110595fbaaf2a4887536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91b5379a8fa59adc23e625f3b5c5e7e42f6ac13740b5110595fbaaf2a4887536","first_computed_at":"2026-05-17T23:51:49.396603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:49.396603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FkcarH2Q0IIfd31EEF2MzD3kAW0p7b48xE10+fd2+56zecDr2QcIS7OuBoQ7aGyWRwsv5sX51xI6hilzk7sfCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:49.397232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79f84ad7c612b047cea5ad80f8573a7aa8f08aaf010c2f7004fe10a998929f20","sha256:4a3cfcc51a240eb1109f9e37c91ea1e146eef954cee6578377739c61ce5032bd"],"state_sha256":"b51416223a5a00c943f3ca06eadbc004d529e6babad966ee52a571f353654817"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAwgdKLXGdVYbVtmdMLqIP2/mAT+tRh+zL43ePHaNMzxql2KSQKGxQb5qN6YncdgPsu6DpdXXG2wPq/Ipa4WAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:47:17.141542Z","bundle_sha256":"08576cd6e8795f13ffb9123ca58cc65ef0e487c83deffa3774013616ceb55e66"}}