{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KICJUFVBJDT245VFNM37JAWZTX","short_pith_number":"pith:KICJUFVB","schema_version":"1.0","canonical_sha256":"52049a16a148e7ae76a56b37f482d99dd2036cc8a58d9fc6e492429e5a27e501","source":{"kind":"arxiv","id":"2110.10632","version":2},"attestation_state":"computed","paper":{"title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johan Ferret, Nathan Grinsztajn, Philippe Preux, Toby Johnstone","submitted_at":"2021-10-20T15:51:14Z","abstract_excerpt":"Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment dynamics are available, reinforcement learning is traditionally used in a tabula rasa setting and must explore and learn everything from scratch. In this paper, we consider the problem of exploiting priors about action sequence equivalence: that is, when different sequences of actions produce the same effect. We propose a new local exploration strategy calibrated to minimize collisions and maximize new state visitations. We show that this strategy can be compu"},"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":"2110.10632","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T15:51:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ce9cad4188de86c7db5aa0718731ae451cefd184a5b1898317070162814b76d","abstract_canon_sha256":"ac4f705d3c3a8bca8bda59bb20a04bada3dedee7b31185f5b479d86cabeabd04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:52.920953Z","signature_b64":"FeAjpYmVXOtiExZEROT5S3/cewj8LNUuHO6HhRZLY4AIdTn75GBf8WBEOIZUGJhkLV/l3bMxd+Gfc+lB15wVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52049a16a148e7ae76a56b37f482d99dd2036cc8a58d9fc6e492429e5a27e501","last_reissued_at":"2026-07-05T03:29:52.920562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:52.920562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johan Ferret, Nathan Grinsztajn, Philippe Preux, Toby Johnstone","submitted_at":"2021-10-20T15:51:14Z","abstract_excerpt":"Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment dynamics are available, reinforcement learning is traditionally used in a tabula rasa setting and must explore and learn everything from scratch. In this paper, we consider the problem of exploiting priors about action sequence equivalence: that is, when different sequences of actions produce the same effect. We propose a new local exploration strategy calibrated to minimize collisions and maximize new state visitations. We show that this strategy can be compu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10632","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/2110.10632/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":"2110.10632","created_at":"2026-07-05T03:29:52.920627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10632v2","created_at":"2026-07-05T03:29:52.920627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10632","created_at":"2026-07-05T03:29:52.920627+00:00"},{"alias_kind":"pith_short_12","alias_value":"KICJUFVBJDT2","created_at":"2026-07-05T03:29:52.920627+00:00"},{"alias_kind":"pith_short_16","alias_value":"KICJUFVBJDT245VF","created_at":"2026-07-05T03:29:52.920627+00:00"},{"alias_kind":"pith_short_8","alias_value":"KICJUFVB","created_at":"2026-07-05T03:29:52.920627+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/KICJUFVBJDT245VFNM37JAWZTX","json":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX.json","graph_json":"https://pith.science/api/pith-number/KICJUFVBJDT245VFNM37JAWZTX/graph.json","events_json":"https://pith.science/api/pith-number/KICJUFVBJDT245VFNM37JAWZTX/events.json","paper":"https://pith.science/paper/KICJUFVB"},"agent_actions":{"view_html":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX","download_json":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX.json","view_paper":"https://pith.science/paper/KICJUFVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10632&json=true","fetch_graph":"https://pith.science/api/pith-number/KICJUFVBJDT245VFNM37JAWZTX/graph.json","fetch_events":"https://pith.science/api/pith-number/KICJUFVBJDT245VFNM37JAWZTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX/action/storage_attestation","attest_author":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX/action/author_attestation","sign_citation":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX/action/citation_signature","submit_replication":"https://pith.science/pith/KICJUFVBJDT245VFNM37JAWZTX/action/replication_record"}},"created_at":"2026-07-05T03:29:52.920627+00:00","updated_at":"2026-07-05T03:29:52.920627+00:00"}