{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EFAO2VVHNF5J2OGAYNZ2SC2RUV","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":"69d4f5abc5144caf79ce48bba16f9b2c8797a36239e2d5cafff13fe5e40dc0b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-16T02:08:17Z","title_canon_sha256":"22e8ce1548d88892e2f2b769bb63ebcd6373b943e1e002ae0c3b2de1b43d89d2"},"schema_version":"1.0","source":{"id":"2405.09760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09760","created_at":"2026-07-05T08:19:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09760v1","created_at":"2026-07-05T08:19:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09760","created_at":"2026-07-05T08:19:48Z"},{"alias_kind":"pith_short_12","alias_value":"EFAO2VVHNF5J","created_at":"2026-07-05T08:19:48Z"},{"alias_kind":"pith_short_16","alias_value":"EFAO2VVHNF5J2OGA","created_at":"2026-07-05T08:19:48Z"},{"alias_kind":"pith_short_8","alias_value":"EFAO2VVH","created_at":"2026-07-05T08:19:48Z"}],"graph_snapshots":[{"event_id":"sha256:6f0f43d73af4b1aa5ecf912ed1abd5685cfde259158e55b1d8f4147d7eedc5f8","target":"graph","created_at":"2026-07-05T08:19:48Z","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/2405.09760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a method to combine reinforcement learning (RL) and imitation learning (IL) using a dynamic, performance-based modulation over learning signals. The proposed method combines RL and behavioral cloning (IL), or corrective feedback in the action space (interactive IL/IIL), by dynamically weighting the losses to be optimized, taking into account the backpropagated gradients used to update the policy and the agent's estimated performance. In this manner, RL and IL/IIL losses are combined by equalizing their impact on the policy's updates, while modulating said impact such that I","authors_text":"Francisco Leiva, Javier Ruiz-del-Solar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-16T02:08:17Z","title":"Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09760","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:ad6d57480f653ff45ef7301a74bce1a316704d9c2fc14d2804fbadb1dd933b4e","target":"record","created_at":"2026-07-05T08:19:48Z","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":"69d4f5abc5144caf79ce48bba16f9b2c8797a36239e2d5cafff13fe5e40dc0b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-16T02:08:17Z","title_canon_sha256":"22e8ce1548d88892e2f2b769bb63ebcd6373b943e1e002ae0c3b2de1b43d89d2"},"schema_version":"1.0","source":{"id":"2405.09760","kind":"arxiv","version":1}},"canonical_sha256":"2140ed56a7697a9d38c0c373a90b51a55934963837addb2b73e7a2dd51f3f47a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2140ed56a7697a9d38c0c373a90b51a55934963837addb2b73e7a2dd51f3f47a","first_computed_at":"2026-07-05T08:19:48.668199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:48.668199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iEM2XhhEfmfkzS54R90aQ0TGDBrnnvfJf2IQ74EYCU6t4DdJ6lK1Etao0XqxaiClvBH5Cc9kDibDt1/dIEBICw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:48.668692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad6d57480f653ff45ef7301a74bce1a316704d9c2fc14d2804fbadb1dd933b4e","sha256:6f0f43d73af4b1aa5ecf912ed1abd5685cfde259158e55b1d8f4147d7eedc5f8"],"state_sha256":"f5e812d1d1fda341781c94c945d7359914214462b4e29afa6d2d414a9df1d746"}