{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4LD4TYM4474M3YNKU3S7RYMIGB","short_pith_number":"pith:4LD4TYM4","schema_version":"1.0","canonical_sha256":"e2c7c9e19ce7f8cde1aaa6e5f8e188307e1fc22b3112f0c9f98c4ebd1f062818","source":{"kind":"arxiv","id":"2111.08575","version":2},"attestation_state":"computed","paper":{"title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Fabien Moutarde, Marin Toromanoff, Raphael Chekroun, Sascha Hornauer","submitted_at":"2021-11-16T15:52:54Z","abstract_excerpt":"Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack of stability. Prior knowledge, e.g. as expert demonstrations, is often available but challenging to leverage to mitigate these issues. In this paper, we propose General Reinforced Imitation (GRI), a novel method which combines benefits from exploration and expert data and is straightforward to implement over any off-policy RL algorithm. We make one simplify"},"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":"2111.08575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-16T15:52:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f0062141e836d326350998b20ac4c9f125ca5190e715adaa39984511d2aa7fb1","abstract_canon_sha256":"e231ed9e7d56124ca613ef1c0783543eb0ad6c1b2775b7f6d036a058a74e77a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:23.594703Z","signature_b64":"U+d5dQh0dcIo85BJY+Uvmc5OwZblkXh1nxwRYk1ntTsAA8im+swC14HHiaA23jnRsqqXVIuDpgtllvTsC+fUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2c7c9e19ce7f8cde1aaa6e5f8e188307e1fc22b3112f0c9f98c4ebd1f062818","last_reissued_at":"2026-07-05T04:24:23.594190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:23.594190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Fabien Moutarde, Marin Toromanoff, Raphael Chekroun, Sascha Hornauer","submitted_at":"2021-11-16T15:52:54Z","abstract_excerpt":"Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack of stability. Prior knowledge, e.g. as expert demonstrations, is often available but challenging to leverage to mitigate these issues. In this paper, we propose General Reinforced Imitation (GRI), a novel method which combines benefits from exploration and expert data and is straightforward to implement over any off-policy RL algorithm. We make one simplify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08575","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/2111.08575/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":"2111.08575","created_at":"2026-07-05T04:24:23.594241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08575v2","created_at":"2026-07-05T04:24:23.594241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08575","created_at":"2026-07-05T04:24:23.594241+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LD4TYM4474M","created_at":"2026-07-05T04:24:23.594241+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LD4TYM4474M3YNK","created_at":"2026-07-05T04:24:23.594241+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LD4TYM4","created_at":"2026-07-05T04:24:23.594241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27994","citing_title":"Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13243","citing_title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27994","citing_title":"Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04355","citing_title":"InterFuserDVS: Event-Enhanced Sensor Fusion for Safe RL-Based Decision Making","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB","json":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB.json","graph_json":"https://pith.science/api/pith-number/4LD4TYM4474M3YNKU3S7RYMIGB/graph.json","events_json":"https://pith.science/api/pith-number/4LD4TYM4474M3YNKU3S7RYMIGB/events.json","paper":"https://pith.science/paper/4LD4TYM4"},"agent_actions":{"view_html":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB","download_json":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB.json","view_paper":"https://pith.science/paper/4LD4TYM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08575&json=true","fetch_graph":"https://pith.science/api/pith-number/4LD4TYM4474M3YNKU3S7RYMIGB/graph.json","fetch_events":"https://pith.science/api/pith-number/4LD4TYM4474M3YNKU3S7RYMIGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB/action/storage_attestation","attest_author":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB/action/author_attestation","sign_citation":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB/action/citation_signature","submit_replication":"https://pith.science/pith/4LD4TYM4474M3YNKU3S7RYMIGB/action/replication_record"}},"created_at":"2026-07-05T04:24:23.594241+00:00","updated_at":"2026-07-05T04:24:23.594241+00:00"}