{"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"}