{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EFAO2VVHNF5J2OGAYNZ2SC2RUV","short_pith_number":"pith:EFAO2VVH","schema_version":"1.0","canonical_sha256":"2140ed56a7697a9d38c0c373a90b51a55934963837addb2b73e7a2dd51f3f47a","source":{"kind":"arxiv","id":"2405.09760","version":1},"attestation_state":"computed","paper":{"title":"Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Francisco Leiva, Javier Ruiz-del-Solar","submitted_at":"2024-05-16T02:08:17Z","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"},"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":"2405.09760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-16T02:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"22e8ce1548d88892e2f2b769bb63ebcd6373b943e1e002ae0c3b2de1b43d89d2","abstract_canon_sha256":"69d4f5abc5144caf79ce48bba16f9b2c8797a36239e2d5cafff13fe5e40dc0b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:48.668692Z","signature_b64":"iEM2XhhEfmfkzS54R90aQ0TGDBrnnvfJf2IQ74EYCU6t4DdJ6lK1Etao0XqxaiClvBH5Cc9kDibDt1/dIEBICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2140ed56a7697a9d38c0c373a90b51a55934963837addb2b73e7a2dd51f3f47a","last_reissued_at":"2026-07-05T08:19:48.668199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:48.668199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Francisco Leiva, Javier Ruiz-del-Solar","submitted_at":"2024-05-16T02:08:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09760","kind":"arxiv","version":1},"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/2405.09760/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":"2405.09760","created_at":"2026-07-05T08:19:48.668271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09760v1","created_at":"2026-07-05T08:19:48.668271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09760","created_at":"2026-07-05T08:19:48.668271+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFAO2VVHNF5J","created_at":"2026-07-05T08:19:48.668271+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFAO2VVHNF5J2OGA","created_at":"2026-07-05T08:19:48.668271+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFAO2VVH","created_at":"2026-07-05T08:19:48.668271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV","json":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV.json","graph_json":"https://pith.science/api/pith-number/EFAO2VVHNF5J2OGAYNZ2SC2RUV/graph.json","events_json":"https://pith.science/api/pith-number/EFAO2VVHNF5J2OGAYNZ2SC2RUV/events.json","paper":"https://pith.science/paper/EFAO2VVH"},"agent_actions":{"view_html":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV","download_json":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV.json","view_paper":"https://pith.science/paper/EFAO2VVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09760&json=true","fetch_graph":"https://pith.science/api/pith-number/EFAO2VVHNF5J2OGAYNZ2SC2RUV/graph.json","fetch_events":"https://pith.science/api/pith-number/EFAO2VVHNF5J2OGAYNZ2SC2RUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV/action/storage_attestation","attest_author":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV/action/author_attestation","sign_citation":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV/action/citation_signature","submit_replication":"https://pith.science/pith/EFAO2VVHNF5J2OGAYNZ2SC2RUV/action/replication_record"}},"created_at":"2026-07-05T08:19:48.668271+00:00","updated_at":"2026-07-05T08:19:48.668271+00:00"}