{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VMJYBYCROGQP3Q5XAYCUTIYPCX","short_pith_number":"pith:VMJYBYCR","canonical_record":{"source":{"id":"1903.07438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T13:43:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e579370d0c6344473f31eac05d1d7a7578bda323f604ddb82b9b15c6d7fc0d7","abstract_canon_sha256":"042e1b7bc75442719eaed9358a46ff4075620c1a9c3aa145cf32bb79af2cdaed"},"schema_version":"1.0"},"canonical_sha256":"ab1380e05171a0fdc3b7060549a30f15d17e07402b82d8e41002b37495581989","source":{"kind":"arxiv","id":"1903.07438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07438","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07438v2","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07438","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_12","alias_value":"VMJYBYCROGQP","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_16","alias_value":"VMJYBYCROGQP3Q5X","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_8","alias_value":"VMJYBYCR","created_at":"2026-07-05T00:35:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VMJYBYCROGQP3Q5XAYCUTIYPCX","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T13:43:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e579370d0c6344473f31eac05d1d7a7578bda323f604ddb82b9b15c6d7fc0d7","abstract_canon_sha256":"042e1b7bc75442719eaed9358a46ff4075620c1a9c3aa145cf32bb79af2cdaed"},"schema_version":"1.0"},"canonical_sha256":"ab1380e05171a0fdc3b7060549a30f15d17e07402b82d8e41002b37495581989","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:18.685760Z","signature_b64":"NiiZNJ+D9OL97wHeqd1wMEiPTLpIWDAWgsfheULQM1Dqt4xMh/YGL0lpmBtaHzJLZuNEg89ec8LAa1GZLSTLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab1380e05171a0fdc3b7060549a30f15d17e07402b82d8e41002b37495581989","last_reissued_at":"2026-07-05T00:35:18.685324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:18.685324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07438","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":"2026-07-05T00:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3s8N5yLiT+EnLLKGDAI8ZvwD/eeAjYAnLfPx/f5E0IZBVkn7FbhiHm0Mtz6C+ymKcARx2ROn/q3ahbbzjF0dBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:37:30.672991Z"},"content_sha256":"34ccb845ba82a66b4728fcf32ded9627c0b01c827f369b13f3bed50d01ab2ddf","schema_version":"1.0","event_id":"sha256:34ccb845ba82a66b4728fcf32ded9627c0b01c827f369b13f3bed50d01ab2ddf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VMJYBYCROGQP3Q5XAYCUTIYPCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Hierarchy for Learning and Transfer in KL-regularized RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Galashov, Arun Ahuja, Dhruva Tirumala, Greg Wayne, Hyeonwoo Noh, Leonard Hasenclever, Nicolas Heess, Razvan Pascanu, Yee Whye Teh","submitted_at":"2019-03-18T13:43:12Z","abstract_excerpt":"As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reusable structure in solution space is likely to become increasingly important. The KL-regularized expected reward objective constitutes one possible tool to this end. It introduces an additional component, a default or prior behavior, which can be learned alongside the policy and as such partially transforms the reinforcement learning problem into one of behavior modelling. In this work we consider the implications of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07438","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.07438/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":"2026-07-05T00:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRDbyLFXXhYCmSR5ZrhDAzi3t7ECqMNH40hJOifXN3qCdV1oB/YkoAnb/LJozCqFxKBObiFvv8JrjVTilLDeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:37:30.673383Z"},"content_sha256":"ddabff3f7d3c2daeae5ac8a58cb251ad5b32f4ff2b7d2960dee3ae370d3059ab","schema_version":"1.0","event_id":"sha256:ddabff3f7d3c2daeae5ac8a58cb251ad5b32f4ff2b7d2960dee3ae370d3059ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/bundle.json","state_url":"https://pith.science/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/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":"2026-07-07T08:37:30Z","links":{"resolver":"https://pith.science/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX","bundle":"https://pith.science/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/bundle.json","state":"https://pith.science/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VMJYBYCROGQP3Q5XAYCUTIYPCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VMJYBYCROGQP3Q5XAYCUTIYPCX","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":"042e1b7bc75442719eaed9358a46ff4075620c1a9c3aa145cf32bb79af2cdaed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T13:43:12Z","title_canon_sha256":"8e579370d0c6344473f31eac05d1d7a7578bda323f604ddb82b9b15c6d7fc0d7"},"schema_version":"1.0","source":{"id":"1903.07438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07438","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07438v2","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07438","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_12","alias_value":"VMJYBYCROGQP","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_16","alias_value":"VMJYBYCROGQP3Q5X","created_at":"2026-07-05T00:35:18Z"},{"alias_kind":"pith_short_8","alias_value":"VMJYBYCR","created_at":"2026-07-05T00:35:18Z"}],"graph_snapshots":[{"event_id":"sha256:ddabff3f7d3c2daeae5ac8a58cb251ad5b32f4ff2b7d2960dee3ae370d3059ab","target":"graph","created_at":"2026-07-05T00:35:18Z","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/1903.07438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reusable structure in solution space is likely to become increasingly important. The KL-regularized expected reward objective constitutes one possible tool to this end. It introduces an additional component, a default or prior behavior, which can be learned alongside the policy and as such partially transforms the reinforcement learning problem into one of behavior modelling. In this work we consider the implications of ","authors_text":"Alexandre Galashov, Arun Ahuja, Dhruva Tirumala, Greg Wayne, Hyeonwoo Noh, Leonard Hasenclever, Nicolas Heess, Razvan Pascanu, Yee Whye Teh","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T13:43:12Z","title":"Exploiting Hierarchy for Learning and Transfer in KL-regularized RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07438","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":"sha256:34ccb845ba82a66b4728fcf32ded9627c0b01c827f369b13f3bed50d01ab2ddf","target":"record","created_at":"2026-07-05T00:35:18Z","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":"042e1b7bc75442719eaed9358a46ff4075620c1a9c3aa145cf32bb79af2cdaed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T13:43:12Z","title_canon_sha256":"8e579370d0c6344473f31eac05d1d7a7578bda323f604ddb82b9b15c6d7fc0d7"},"schema_version":"1.0","source":{"id":"1903.07438","kind":"arxiv","version":2}},"canonical_sha256":"ab1380e05171a0fdc3b7060549a30f15d17e07402b82d8e41002b37495581989","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab1380e05171a0fdc3b7060549a30f15d17e07402b82d8e41002b37495581989","first_computed_at":"2026-07-05T00:35:18.685324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:18.685324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NiiZNJ+D9OL97wHeqd1wMEiPTLpIWDAWgsfheULQM1Dqt4xMh/YGL0lpmBtaHzJLZuNEg89ec8LAa1GZLSTLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:18.685760Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34ccb845ba82a66b4728fcf32ded9627c0b01c827f369b13f3bed50d01ab2ddf","sha256:ddabff3f7d3c2daeae5ac8a58cb251ad5b32f4ff2b7d2960dee3ae370d3059ab"],"state_sha256":"fcc3a93495775e33c368adaea20ce59328034a687b83dd89bef47f6d6c90ff94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJZZRqHpZNoIUu2rem0Dr2/s57g/z9K58xwzdIqYXgJasCkcM1Mtsw1oT6Jw2xaJmvlv+AC1SPoA2uQEIvFqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:37:30.675326Z","bundle_sha256":"6768e2aa143428d06f591c7e4c15c7f1f33a3cef397ad767094f11a8bababae4"}}