{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UCAE6QYG67EJ5BHWDZTR5JW5NW","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":"9031e78a165e63e59ad40af6b054ba0b4fcb3e62e10a23c58cff835555252568","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-07T15:19:22Z","title_canon_sha256":"9324b4ac5151db7bf28b97cef6b39703cdb279e26564b96ee63f8ee5e24e6fc0"},"schema_version":"1.0","source":{"id":"1912.03517","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03517","created_at":"2026-07-05T01:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03517v3","created_at":"2026-07-05T01:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03517","created_at":"2026-07-05T01:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"UCAE6QYG67EJ","created_at":"2026-07-05T01:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"UCAE6QYG67EJ5BHW","created_at":"2026-07-05T01:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"UCAE6QYG","created_at":"2026-07-05T01:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:876204a254e2b12001a7c5e6896c6b70b981fe8c21c3dfd0b2bd3bc38d2b9a6e","target":"graph","created_at":"2026-07-05T01:27:20Z","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/1912.03517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (SSP) formulation, where an agent has to achieve a goal state while minimizing the cumulative cost. Despite the popularity of this setting, the exploration-exploitation dilemma has been sparsely studied in general SSP problems, with most of the theoretical literature focusing on different problems (i.e., fixed-horizon and infinite-horizon) or making the restrictive loop-free SSP assumption (i.e., no state can be visit","authors_text":"Alessandro Lazaric, Evrard Garcelon, Jean Tarbouriech, Matteo Pirotta, Michal Valko","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-07T15:19:22Z","title":"No-Regret Exploration in Goal-Oriented Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03517","kind":"arxiv","version":3},"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":"sha256:314b0fa47ad143a62f4be2427afe9bb36558ed05495bf13223c3743d03ff7ad4","target":"record","created_at":"2026-07-05T01:27:20Z","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":"9031e78a165e63e59ad40af6b054ba0b4fcb3e62e10a23c58cff835555252568","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-07T15:19:22Z","title_canon_sha256":"9324b4ac5151db7bf28b97cef6b39703cdb279e26564b96ee63f8ee5e24e6fc0"},"schema_version":"1.0","source":{"id":"1912.03517","kind":"arxiv","version":3}},"canonical_sha256":"a0804f4306f7c89e84f61e671ea6dd6db20188c9f63340c59181464a9fa440bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0804f4306f7c89e84f61e671ea6dd6db20188c9f63340c59181464a9fa440bd","first_computed_at":"2026-07-05T01:27:20.222550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:20.222550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vJgdlPr4wBIKXQK8oK3+FFh4eB09iNWcB1BLs27JMIo1Ly1I96B77n7sYhiJcmbFQZByZD4owiD8mdkfzVcOCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:20.222961Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03517","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:314b0fa47ad143a62f4be2427afe9bb36558ed05495bf13223c3743d03ff7ad4","sha256:876204a254e2b12001a7c5e6896c6b70b981fe8c21c3dfd0b2bd3bc38d2b9a6e"],"state_sha256":"82daa87512af35840e24d56100036e0b8b7e48eb05f23de874e7423f2a1e83a5"}