{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U5MQWD7VA2ZUCKDIW7MEQAD46P","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":"02926e52bd49e19b6ef099104e877f92c714e5948c9cb10079cbb610e4ec005c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T16:52:26Z","title_canon_sha256":"a9c3b0c13c6b6a6cd0fdf4181b43cf967f923765a649e247f325660ba94e1784"},"schema_version":"1.0","source":{"id":"2402.13930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13930","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13930v1","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13930","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_12","alias_value":"U5MQWD7VA2ZU","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_16","alias_value":"U5MQWD7VA2ZUCKDI","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_8","alias_value":"U5MQWD7V","created_at":"2026-07-05T08:43:53Z"}],"graph_snapshots":[{"event_id":"sha256:d3c5df660dbdcf80706d43d6964233879cad92cf3a72472f821eeab88724c246","target":"graph","created_at":"2026-07-05T08:43:53Z","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/2402.13930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching procedure. This approach builds on a proper Approximate Policy Evaluation (APE) scheme to provide a perturbation that carefully leads the local guides towards better actions. We evaluated our method on a set of classical Reinforcement Learning problems, including safety-critical systems where the agent cannot enter some areas at the risk of triggering ca","authors_text":"Bogdan Robu, Christophe Prieur, Ludovic Dos Santos, Merwan Barlier, Paul Daoudi","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T16:52:26Z","title":"Enhancing Reinforcement Learning Agents with Local Guides"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13930","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:db77e4c8e9101d4d31d42d0f9666135643c24612f3d8b4c1c6bbb24154d82d74","target":"record","created_at":"2026-07-05T08:43:53Z","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":"02926e52bd49e19b6ef099104e877f92c714e5948c9cb10079cbb610e4ec005c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T16:52:26Z","title_canon_sha256":"a9c3b0c13c6b6a6cd0fdf4181b43cf967f923765a649e247f325660ba94e1784"},"schema_version":"1.0","source":{"id":"2402.13930","kind":"arxiv","version":1}},"canonical_sha256":"a7590b0ff506b3412868b7d848007cf3df528b01ae0ee51c995bad133975ca88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7590b0ff506b3412868b7d848007cf3df528b01ae0ee51c995bad133975ca88","first_computed_at":"2026-07-05T08:43:53.339463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:53.339463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqMFOhtm5UhjwGzSN991YCu0bxMaheZezHoSYvVw4lvpRezjOFmWUE2v28MQM4TK6upmvAGgsIDQhfIHVB21Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:53.339917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db77e4c8e9101d4d31d42d0f9666135643c24612f3d8b4c1c6bbb24154d82d74","sha256:d3c5df660dbdcf80706d43d6964233879cad92cf3a72472f821eeab88724c246"],"state_sha256":"fb7a3bc128f8c9e176b5352144323b442a41b1a3b00f927caa6ee280c6dda217"}