{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4LD4TYM4474M3YNKU3S7RYMIGB","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":"e231ed9e7d56124ca613ef1c0783543eb0ad6c1b2775b7f6d036a058a74e77a6","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-16T15:52:54Z","title_canon_sha256":"f0062141e836d326350998b20ac4c9f125ca5190e715adaa39984511d2aa7fb1"},"schema_version":"1.0","source":{"id":"2111.08575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08575","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08575v2","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08575","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"4LD4TYM4474M","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_16","alias_value":"4LD4TYM4474M3YNK","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_8","alias_value":"4LD4TYM4","created_at":"2026-07-05T04:24:23Z"}],"graph_snapshots":[{"event_id":"sha256:4212c64dbc96fcf61e89b6024d2f0bb8e5a8ee58701a0c2cd0e9850f6398ab9f","target":"graph","created_at":"2026-07-05T04:24:23Z","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/2111.08575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fabien Moutarde, Marin Toromanoff, Raphael Chekroun, Sascha Hornauer","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-16T15:52:54Z","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08575","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":"sha256:8832e847efc527418eeceadc725b2e135b67476ee126fb2bc797e28a83b12232","target":"record","created_at":"2026-07-05T04:24:23Z","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":"e231ed9e7d56124ca613ef1c0783543eb0ad6c1b2775b7f6d036a058a74e77a6","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-16T15:52:54Z","title_canon_sha256":"f0062141e836d326350998b20ac4c9f125ca5190e715adaa39984511d2aa7fb1"},"schema_version":"1.0","source":{"id":"2111.08575","kind":"arxiv","version":2}},"canonical_sha256":"e2c7c9e19ce7f8cde1aaa6e5f8e188307e1fc22b3112f0c9f98c4ebd1f062818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2c7c9e19ce7f8cde1aaa6e5f8e188307e1fc22b3112f0c9f98c4ebd1f062818","first_computed_at":"2026-07-05T04:24:23.594190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:23.594190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U+d5dQh0dcIo85BJY+Uvmc5OwZblkXh1nxwRYk1ntTsAA8im+swC14HHiaA23jnRsqqXVIuDpgtllvTsC+fUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:23.594703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8832e847efc527418eeceadc725b2e135b67476ee126fb2bc797e28a83b12232","sha256:4212c64dbc96fcf61e89b6024d2f0bb8e5a8ee58701a0c2cd0e9850f6398ab9f"],"state_sha256":"62304b9cd780f3bfe45a2990eec46a162c503facd6c4e6bf27053e32eea39686"}