{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SIJUXAQSKXKAJDFYLB2N5BFIG6","short_pith_number":"pith:SIJUXAQS","canonical_record":{"source":{"id":"1905.10016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:19:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03b24c99b086fe95857de8dd5307191f4a8111ec8d65ca6de71f1bdadfde85c0","abstract_canon_sha256":"2a5af53eb63331d1f0a09230833e9d81ce9690b12fe11786e7ae4c9850984645"},"schema_version":"1.0"},"canonical_sha256":"92134b821255d4048cb85874de84a837a3a5f6b6be75758bcb96a3af8ca3682f","source":{"kind":"arxiv","id":"1905.10016","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10016","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10016v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10016","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"SIJUXAQSKXKA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SIJUXAQSKXKAJDFY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SIJUXAQS","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SIJUXAQSKXKAJDFYLB2N5BFIG6","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10016","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:19:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03b24c99b086fe95857de8dd5307191f4a8111ec8d65ca6de71f1bdadfde85c0","abstract_canon_sha256":"2a5af53eb63331d1f0a09230833e9d81ce9690b12fe11786e7ae4c9850984645"},"schema_version":"1.0"},"canonical_sha256":"92134b821255d4048cb85874de84a837a3a5f6b6be75758bcb96a3af8ca3682f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.591226Z","signature_b64":"urYKXQ4lSiGGfteKNOMladDWPtytOSBxtwd4mpjw+hqKhXB1GBH8FAz4Qvg3n9V6iZ9d37duH1QS1hTjcp9zAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92134b821255d4048cb85874de84a837a3a5f6b6be75758bcb96a3af8ca3682f","last_reissued_at":"2026-05-17T23:43:32.590855Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.590855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10016","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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Le9/33zBN/gJWCvSauSsPPblvyaHqd0xHHptusq1X1uFohrkIwyLf8friMNqtEwu69pOYhOOjN4cCjri8nqCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:55:18.645106Z"},"content_sha256":"6587a45b2237d169566f3df7780c9046534b0a27627a0e4bad05790469ffea6f","schema_version":"1.0","event_id":"sha256:6587a45b2237d169566f3df7780c9046534b0a27627a0e4bad05790469ffea6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SIJUXAQSKXKAJDFYLB2N5BFIG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Micro-Objective Perspective of Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changjian Li, Krzysztof Czarnecki","submitted_at":"2019-05-24T03:19:59Z","abstract_excerpt":"The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution of the performance. In this paper, we introduce micro-objective reinforcement learning --- an alternative RL formalism that overcomes this issue. In this new formulation, a RL task is specified by a set of micro-objectives, which are constructs that specify the desirability or undesirability of events. In addition, micro-objectives allow prior knowledge in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10016","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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uN8Mq/Vm+xmrvAs3Gm35/O3F8F17RKqaU60nzzMUdReIfowkXExvUpqIIBouUkiuNQDb5OK0QtagtwArtFIpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T04:55:18.645740Z"},"content_sha256":"9ca7e3ea8fcfae90544d62021d331b4ddccf2532114d2284af158d3c9d280bb1","schema_version":"1.0","event_id":"sha256:9ca7e3ea8fcfae90544d62021d331b4ddccf2532114d2284af158d3c9d280bb1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/bundle.json","state_url":"https://pith.science/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/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":"2026-06-09T04:55:18Z","links":{"resolver":"https://pith.science/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6","bundle":"https://pith.science/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/bundle.json","state":"https://pith.science/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SIJUXAQSKXKAJDFYLB2N5BFIG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SIJUXAQSKXKAJDFYLB2N5BFIG6","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":"2a5af53eb63331d1f0a09230833e9d81ce9690b12fe11786e7ae4c9850984645","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:19:59Z","title_canon_sha256":"03b24c99b086fe95857de8dd5307191f4a8111ec8d65ca6de71f1bdadfde85c0"},"schema_version":"1.0","source":{"id":"1905.10016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10016","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10016v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10016","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"SIJUXAQSKXKA","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SIJUXAQSKXKAJDFY","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SIJUXAQS","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:9ca7e3ea8fcfae90544d62021d331b4ddccf2532114d2284af158d3c9d280bb1","target":"graph","created_at":"2026-05-17T23:43:32Z","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":"The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution of the performance. In this paper, we introduce micro-objective reinforcement learning --- an alternative RL formalism that overcomes this issue. In this new formulation, a RL task is specified by a set of micro-objectives, which are constructs that specify the desirability or undesirability of events. In addition, micro-objectives allow prior knowledge in t","authors_text":"Changjian Li, Krzysztof Czarnecki","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:19:59Z","title":"A Micro-Objective Perspective of Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10016","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":"sha256:6587a45b2237d169566f3df7780c9046534b0a27627a0e4bad05790469ffea6f","target":"record","created_at":"2026-05-17T23:43:32Z","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":"2a5af53eb63331d1f0a09230833e9d81ce9690b12fe11786e7ae4c9850984645","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T03:19:59Z","title_canon_sha256":"03b24c99b086fe95857de8dd5307191f4a8111ec8d65ca6de71f1bdadfde85c0"},"schema_version":"1.0","source":{"id":"1905.10016","kind":"arxiv","version":2}},"canonical_sha256":"92134b821255d4048cb85874de84a837a3a5f6b6be75758bcb96a3af8ca3682f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92134b821255d4048cb85874de84a837a3a5f6b6be75758bcb96a3af8ca3682f","first_computed_at":"2026-05-17T23:43:32.590855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:32.590855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"urYKXQ4lSiGGfteKNOMladDWPtytOSBxtwd4mpjw+hqKhXB1GBH8FAz4Qvg3n9V6iZ9d37duH1QS1hTjcp9zAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:32.591226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6587a45b2237d169566f3df7780c9046534b0a27627a0e4bad05790469ffea6f","sha256:9ca7e3ea8fcfae90544d62021d331b4ddccf2532114d2284af158d3c9d280bb1"],"state_sha256":"bf99128669e377a2d08bcb3aece67565cf3d70a7f1ac4f307b9851c3bac6e9fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PjlMV6AGiXHf4PYYPidKcuLIHcgfqyCzDkpzfC2/MzHSTiq/83hh8Lxzvuucv7+813RNrO46sEJcn017e1mBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T04:55:18.649577Z","bundle_sha256":"0543fdee6650c87ebb08e377fe4c6aac6feebf32949ff81a8b75385ccace5507"}}