{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C3ZE53JDAO2KKLJKBGZE5AVYGD","short_pith_number":"pith:C3ZE53JD","schema_version":"1.0","canonical_sha256":"16f24eed2303b4a52d2a09b24e82b830ebe732e9b953ba8eee61adb025502469","source":{"kind":"arxiv","id":"2111.12045","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Multi-Goal Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko, Omar Darwiche Domingues, Pierre M\\'enard","submitted_at":"2021-11-23T17:59:50Z","abstract_excerpt":"We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reaching states to adaptively target goals that are neither too difficult nor too easy. We show how AdaGoal can be used to tackle the objective of learning an $\\epsilon$-optimal goal-conditioned policy for the (initially unknown) set of goal states that are reachable within $L$ steps in expectation from a reference state $s_0$ in a reward-free Markov decision process. In the tabular case with $S$ states and $A$ actions, ou"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.12045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-23T17:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"19330ccb0db822dd1f532954b9e49820748371c8a319f138d3adf30726f83fe3","abstract_canon_sha256":"e76800a4cb844850215371dbbaa9df106d2e86ad24ca022e93e8f7de82b9be48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:42.794619Z","signature_b64":"fWSvoP4yVIY/q1Yi/7P/i3q/M2+/2pya78os5oo6d/4Wo8OQTCs4YEWr6Hlziz6VcfR6uUaEwhJ66H+VVeOeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16f24eed2303b4a52d2a09b24e82b830ebe732e9b953ba8eee61adb025502469","last_reissued_at":"2026-07-05T03:59:42.794117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:42.794117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Multi-Goal Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko, Omar Darwiche Domingues, Pierre M\\'enard","submitted_at":"2021-11-23T17:59:50Z","abstract_excerpt":"We introduce a generic strategy for provably efficient multi-goal exploration. It relies on AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reaching states to adaptively target goals that are neither too difficult nor too easy. We show how AdaGoal can be used to tackle the objective of learning an $\\epsilon$-optimal goal-conditioned policy for the (initially unknown) set of goal states that are reachable within $L$ steps in expectation from a reference state $s_0$ in a reward-free Markov decision process. In the tabular case with $S$ states and $A$ actions, ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12045","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.12045/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.12045","created_at":"2026-07-05T03:59:42.794175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12045v2","created_at":"2026-07-05T03:59:42.794175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12045","created_at":"2026-07-05T03:59:42.794175+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3ZE53JDAO2K","created_at":"2026-07-05T03:59:42.794175+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3ZE53JDAO2KKLJK","created_at":"2026-07-05T03:59:42.794175+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3ZE53JD","created_at":"2026-07-05T03:59:42.794175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD","json":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD.json","graph_json":"https://pith.science/api/pith-number/C3ZE53JDAO2KKLJKBGZE5AVYGD/graph.json","events_json":"https://pith.science/api/pith-number/C3ZE53JDAO2KKLJKBGZE5AVYGD/events.json","paper":"https://pith.science/paper/C3ZE53JD"},"agent_actions":{"view_html":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD","download_json":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD.json","view_paper":"https://pith.science/paper/C3ZE53JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12045&json=true","fetch_graph":"https://pith.science/api/pith-number/C3ZE53JDAO2KKLJKBGZE5AVYGD/graph.json","fetch_events":"https://pith.science/api/pith-number/C3ZE53JDAO2KKLJKBGZE5AVYGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD/action/storage_attestation","attest_author":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD/action/author_attestation","sign_citation":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD/action/citation_signature","submit_replication":"https://pith.science/pith/C3ZE53JDAO2KKLJKBGZE5AVYGD/action/replication_record"}},"created_at":"2026-07-05T03:59:42.794175+00:00","updated_at":"2026-07-05T03:59:42.794175+00:00"}