{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZYINZIHLQNLUMIPSSYSJWFXT62","short_pith_number":"pith:ZYINZIHL","canonical_record":{"source":{"id":"1801.00056","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T23:07:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8079f8e09b7c215f6e6d142a69f9504f3b53b80bedebd95dad0f6f3a13819a24","abstract_canon_sha256":"35bb8de6b9eda3543155d9e40c8c602635a195a518394a89dcd33c743308cdb1"},"schema_version":"1.0"},"canonical_sha256":"ce10dca0eb83574621f296249b16f3f6909ce215977735484e2f6d2a8f1e79f1","source":{"kind":"arxiv","id":"1801.00056","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00056","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00056v2","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00056","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZYINZIHLQNLU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZYINZIHLQNLUMIPS","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZYINZIHL","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZYINZIHLQNLUMIPSSYSJWFXT62","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00056","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T23:07:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8079f8e09b7c215f6e6d142a69f9504f3b53b80bedebd95dad0f6f3a13819a24","abstract_canon_sha256":"35bb8de6b9eda3543155d9e40c8c602635a195a518394a89dcd33c743308cdb1"},"schema_version":"1.0"},"canonical_sha256":"ce10dca0eb83574621f296249b16f3f6909ce215977735484e2f6d2a8f1e79f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:16.592775Z","signature_b64":"5sgP54RC775zoQgdMt4kKbSVIfmnCLxduuKv/X1icEL6fl+tOR6VD+3SlotQa5pJ9/oi9bYLmA2Lh4TEm7JzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce10dca0eb83574621f296249b16f3f6909ce215977735484e2f6d2a8f1e79f1","last_reissued_at":"2026-05-18T00:19:16.592171Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:16.592171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00056","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":"2026-05-18T00:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPhMkHC2OdH62HaG2HPdn5CgS82b50ShPEoGSWf/6izM13//ZQR6wR5MYHgLk9+pRhEe1+P6jMEK84eSUKuOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:12:09.194058Z"},"content_sha256":"24a296ffd330f886e4c9829740b047c0fa1af444b6901a610556bc6b2d1c1b4e","schema_version":"1.0","event_id":"sha256:24a296ffd330f886e4c9829740b047c0fa1af444b6901a610556bc6b2d1c1b4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZYINZIHLQNLUMIPSSYSJWFXT62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"f-Divergence constrained policy improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Belousov, Jan Peters","submitted_at":"2017-12-29T23:07:26Z","abstract_excerpt":"To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of distance well but also yields closed-form solutions. In this paper, we consider a more general class of f-divergences and derive the corresponding policy update rules. The generic solution is expressed through the derivative of the convex conjugate function to f and includes the K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00056","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":"2026-05-18T00:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WseMCsiIWWXao6WXrMrzF4QYY/OQHAchTT19kBwHX76EqpNZVkZsmoxJgK29MQUJQag98r8b74AdSC1sCQUWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:12:09.194742Z"},"content_sha256":"8411f985767cb274b6cf3a763a393ff6258ad80cc64a6aa5bf126d0a9e47687b","schema_version":"1.0","event_id":"sha256:8411f985767cb274b6cf3a763a393ff6258ad80cc64a6aa5bf126d0a9e47687b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/bundle.json","state_url":"https://pith.science/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/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":"2026-06-05T03:12:09Z","links":{"resolver":"https://pith.science/pith/ZYINZIHLQNLUMIPSSYSJWFXT62","bundle":"https://pith.science/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/bundle.json","state":"https://pith.science/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYINZIHLQNLUMIPSSYSJWFXT62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZYINZIHLQNLUMIPSSYSJWFXT62","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":"35bb8de6b9eda3543155d9e40c8c602635a195a518394a89dcd33c743308cdb1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T23:07:26Z","title_canon_sha256":"8079f8e09b7c215f6e6d142a69f9504f3b53b80bedebd95dad0f6f3a13819a24"},"schema_version":"1.0","source":{"id":"1801.00056","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00056","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00056v2","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00056","created_at":"2026-05-18T00:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZYINZIHLQNLU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZYINZIHLQNLUMIPS","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZYINZIHL","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:8411f985767cb274b6cf3a763a393ff6258ad80cc64a6aa5bf126d0a9e47687b","target":"graph","created_at":"2026-05-18T00:19:16Z","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":"To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of distance well but also yields closed-form solutions. In this paper, we consider a more general class of f-divergences and derive the corresponding policy update rules. The generic solution is expressed through the derivative of the convex conjugate function to f and includes the K","authors_text":"Boris Belousov, Jan Peters","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T23:07:26Z","title":"f-Divergence constrained policy improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00056","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":"sha256:24a296ffd330f886e4c9829740b047c0fa1af444b6901a610556bc6b2d1c1b4e","target":"record","created_at":"2026-05-18T00:19:16Z","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":"35bb8de6b9eda3543155d9e40c8c602635a195a518394a89dcd33c743308cdb1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T23:07:26Z","title_canon_sha256":"8079f8e09b7c215f6e6d142a69f9504f3b53b80bedebd95dad0f6f3a13819a24"},"schema_version":"1.0","source":{"id":"1801.00056","kind":"arxiv","version":2}},"canonical_sha256":"ce10dca0eb83574621f296249b16f3f6909ce215977735484e2f6d2a8f1e79f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce10dca0eb83574621f296249b16f3f6909ce215977735484e2f6d2a8f1e79f1","first_computed_at":"2026-05-18T00:19:16.592171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:16.592171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5sgP54RC775zoQgdMt4kKbSVIfmnCLxduuKv/X1icEL6fl+tOR6VD+3SlotQa5pJ9/oi9bYLmA2Lh4TEm7JzBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:16.592775Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00056","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24a296ffd330f886e4c9829740b047c0fa1af444b6901a610556bc6b2d1c1b4e","sha256:8411f985767cb274b6cf3a763a393ff6258ad80cc64a6aa5bf126d0a9e47687b"],"state_sha256":"33fbf35a0ec55d939a2fc6d0634a96bd105096059135526c8d89ff85daca29d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FB+F3C64mOpR1KvGnRG85zwe8e3JZduipVvLHi17BZwHtIfu1u+caie8fcPByDmhvvCw+1YOnXAa8SgMFiQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T03:12:09.198697Z","bundle_sha256":"a28e871d24ca3f3e8bf8096cb2a6eeec004d068754f55880babfb980e61fcd06"}}