{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KICJUFVBJDT245VFNM37JAWZTX","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":"ac4f705d3c3a8bca8bda59bb20a04bada3dedee7b31185f5b479d86cabeabd04","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T15:51:14Z","title_canon_sha256":"2ce9cad4188de86c7db5aa0718731ae451cefd184a5b1898317070162814b76d"},"schema_version":"1.0","source":{"id":"2110.10632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10632","created_at":"2026-07-05T03:29:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10632v2","created_at":"2026-07-05T03:29:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10632","created_at":"2026-07-05T03:29:52Z"},{"alias_kind":"pith_short_12","alias_value":"KICJUFVBJDT2","created_at":"2026-07-05T03:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"KICJUFVBJDT245VF","created_at":"2026-07-05T03:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"KICJUFVB","created_at":"2026-07-05T03:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:7807ed658effaaedebf7d11a741e1c6d0f3088f11f66c1c1aa56f9c95be83ebf","target":"graph","created_at":"2026-07-05T03:29:52Z","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/2110.10632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Johan Ferret, Nathan Grinsztajn, Philippe Preux, Toby Johnstone","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T15:51:14Z","title":"More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10632","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:fa5ac59f0a647989c3f70b264118876e2ac7fd977c7a0f7e4fff3c1c6d5258f4","target":"record","created_at":"2026-07-05T03:29:52Z","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":"ac4f705d3c3a8bca8bda59bb20a04bada3dedee7b31185f5b479d86cabeabd04","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T15:51:14Z","title_canon_sha256":"2ce9cad4188de86c7db5aa0718731ae451cefd184a5b1898317070162814b76d"},"schema_version":"1.0","source":{"id":"2110.10632","kind":"arxiv","version":2}},"canonical_sha256":"52049a16a148e7ae76a56b37f482d99dd2036cc8a58d9fc6e492429e5a27e501","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52049a16a148e7ae76a56b37f482d99dd2036cc8a58d9fc6e492429e5a27e501","first_computed_at":"2026-07-05T03:29:52.920562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:52.920562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FeAjpYmVXOtiExZEROT5S3/cewj8LNUuHO6HhRZLY4AIdTn75GBf8WBEOIZUGJhkLV/l3bMxd+Gfc+lB15wVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:52.920953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa5ac59f0a647989c3f70b264118876e2ac7fd977c7a0f7e4fff3c1c6d5258f4","sha256:7807ed658effaaedebf7d11a741e1c6d0f3088f11f66c1c1aa56f9c95be83ebf"],"state_sha256":"711edf8726a66934a863767f261f488821f09979c7c17de673d8b902de77f064"}