{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5V22DS6X57V2W34UURMKISCCP5","short_pith_number":"pith:5V22DS6X","schema_version":"1.0","canonical_sha256":"ed75a1cbd7efebab6f94a458a448427f6a04f3b4e1abc7af538d281342d41872","source":{"kind":"arxiv","id":"2209.12072","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Letian Wang, Ruobing Chen, Tong Zhou, Wenshuo Wang, Yu Liu","submitted_at":"2022-09-24T18:50:30Z","abstract_excerpt":"Efficient and effective exploration in continuous space is a central problem in applying reinforcement learning (RL) to autonomous driving. Skills learned from expert demonstrations or designed for specific tasks can benefit the exploration, but they are usually costly-collected, unbalanced/sub-optimal, or failing to transfer to diverse tasks. However, human drivers can adapt to varied driving tasks without demonstrations by taking efficient and structural explorations in the entire skill space rather than a limited space with task-specific skills. Inspired by the above fact, we propose an RL "},"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":"2209.12072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-24T18:50:30Z","cross_cats_sorted":[],"title_canon_sha256":"b440f2edbcfde8861f237cc35f232e16bba3efa74db2288a6f8bd8c800c4754b","abstract_canon_sha256":"b12c80d51ade39aa6f8fa55b6436e804dfacf5d63d965c3f10c9ed98e6e59bf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:48.585857Z","signature_b64":"FhKv9xyN5jg+Wa+morgsXiN1nYxR9Q7iZ8SsRdYuJeC+IxTc/8bjIZkAzq6ZBS2nsiGJ7jMFon3Rs422+MOgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed75a1cbd7efebab6f94a458a448427f6a04f3b4e1abc7af538d281342d41872","last_reissued_at":"2026-07-05T05:00:48.585392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:48.585392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Letian Wang, Ruobing Chen, Tong Zhou, Wenshuo Wang, Yu Liu","submitted_at":"2022-09-24T18:50:30Z","abstract_excerpt":"Efficient and effective exploration in continuous space is a central problem in applying reinforcement learning (RL) to autonomous driving. Skills learned from expert demonstrations or designed for specific tasks can benefit the exploration, but they are usually costly-collected, unbalanced/sub-optimal, or failing to transfer to diverse tasks. However, human drivers can adapt to varied driving tasks without demonstrations by taking efficient and structural explorations in the entire skill space rather than a limited space with task-specific skills. Inspired by the above fact, we propose an RL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12072","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/2209.12072/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":"2209.12072","created_at":"2026-07-05T05:00:48.585451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12072v1","created_at":"2026-07-05T05:00:48.585451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12072","created_at":"2026-07-05T05:00:48.585451+00:00"},{"alias_kind":"pith_short_12","alias_value":"5V22DS6X57V2","created_at":"2026-07-05T05:00:48.585451+00:00"},{"alias_kind":"pith_short_16","alias_value":"5V22DS6X57V2W34U","created_at":"2026-07-05T05:00:48.585451+00:00"},{"alias_kind":"pith_short_8","alias_value":"5V22DS6X","created_at":"2026-07-05T05:00:48.585451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06347","citing_title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5","json":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5.json","graph_json":"https://pith.science/api/pith-number/5V22DS6X57V2W34UURMKISCCP5/graph.json","events_json":"https://pith.science/api/pith-number/5V22DS6X57V2W34UURMKISCCP5/events.json","paper":"https://pith.science/paper/5V22DS6X"},"agent_actions":{"view_html":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5","download_json":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5.json","view_paper":"https://pith.science/paper/5V22DS6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12072&json=true","fetch_graph":"https://pith.science/api/pith-number/5V22DS6X57V2W34UURMKISCCP5/graph.json","fetch_events":"https://pith.science/api/pith-number/5V22DS6X57V2W34UURMKISCCP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5/action/storage_attestation","attest_author":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5/action/author_attestation","sign_citation":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5/action/citation_signature","submit_replication":"https://pith.science/pith/5V22DS6X57V2W34UURMKISCCP5/action/replication_record"}},"created_at":"2026-07-05T05:00:48.585451+00:00","updated_at":"2026-07-05T05:00:48.585451+00:00"}