{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:2VUKCFTI4K4PXMSURYMQ5ATPQT","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":"a6a4325f1ebd90cc2ae784b85a80bdee98fa20c00c89d842593c1bf150dc1bf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-16T23:30:08Z","title_canon_sha256":"a2704dadb125920ee2b2f5fa174702532f59850bf500e38ac3b9c4e7ab9a9ab0"},"schema_version":"1.0","source":{"id":"1410.4604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.4604","created_at":"2026-05-18T02:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"1410.4604v1","created_at":"2026-05-18T02:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.4604","created_at":"2026-05-18T02:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"2VUKCFTI4K4P","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"2VUKCFTI4K4PXMSU","created_at":"2026-05-18T12:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"2VUKCFTI","created_at":"2026-05-18T12:28:11Z"}],"graph_snapshots":[{"event_id":"sha256:ab912a8a169dc69449529341ee7bd9924ebba3cba213b566e90c4f4ce4d44a0c","target":"graph","created_at":"2026-05-18T02:39:55Z","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":"In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration. However, such an approach generally depends on the domain, viz., the scale of the rewards must be known, and the feature representation must have a constant norm. We present a simple approach that performs optimistic initialization with less dependence on the domain.","authors_text":"Marlos C. Machado, Michael Bowling, Sriram Srinivasan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-16T23:30:08Z","title":"Domain-Independent Optimistic Initialization for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.4604","kind":"arxiv","version":1},"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:e5850ea030f856d3491a1e371c9e4f8fd9b6e06f8543678b8d44732b206c158a","target":"record","created_at":"2026-05-18T02:39:55Z","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":"a6a4325f1ebd90cc2ae784b85a80bdee98fa20c00c89d842593c1bf150dc1bf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-16T23:30:08Z","title_canon_sha256":"a2704dadb125920ee2b2f5fa174702532f59850bf500e38ac3b9c4e7ab9a9ab0"},"schema_version":"1.0","source":{"id":"1410.4604","kind":"arxiv","version":1}},"canonical_sha256":"d568a11668e2b8fbb2548e190e826f84e83873bb39bae72c393a68cb20efe612","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d568a11668e2b8fbb2548e190e826f84e83873bb39bae72c393a68cb20efe612","first_computed_at":"2026-05-18T02:39:55.173861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:39:55.173861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPK8rDzOJCMsafbGBKuKbuB2RdDUw29cP9I/enODsuUy1V33hZoGV4OfoJbDLoEWfcoCy8wOPhjqIs9fdp0PDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:39:55.174292Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.4604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5850ea030f856d3491a1e371c9e4f8fd9b6e06f8543678b8d44732b206c158a","sha256:ab912a8a169dc69449529341ee7bd9924ebba3cba213b566e90c4f4ce4d44a0c"],"state_sha256":"85b6497f546785215889c7f0b79e174a218e8c9ed5ef0b0c70c39eb50c67a2d9"}