{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FZBBW3YMEEFEDTJS353XWH7K6E","short_pith_number":"pith:FZBBW3YM","schema_version":"1.0","canonical_sha256":"2e421b6f0c210a41cd32df777b1feaf1378c2e5e2d612b1bfe2b93cfa79fddf7","source":{"kind":"arxiv","id":"1806.06161","version":2},"attestation_state":"computed","paper":{"title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Apoorva Sharma, Boris Ivanovic, James Harrison, Marco Pavone, Mo Chen","submitted_at":"2018-06-16T00:59:11Z","abstract_excerpt":"Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation, goal-directed tasks whose natural reward function is sparse remain intractable for state-of-the-art model-free algorithms for continuous control. The bottleneck in these tasks is the prohibitive amount of exploration required to obtain a learning signal from the initial state of the system. In this work, we leverage physical priors in the form of an approximate "},"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":"1806.06161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-06-16T00:59:11Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"b3bdcdd775e035bda25d10529725f541d7e4502bbe2d470dc6ea32a2cd8d6a75","abstract_canon_sha256":"83516cbd2fee77016cad3f71a81fea55f9c2af25edd034062c4a26931ba9fdb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:38.856688Z","signature_b64":"+ptdaZkpdLZfbl5CtiBdPDNkJM0BRh8nvO4H4NbGPzqfrjq5qJC+n/H7lJONuNfR1T3AhNfh71uJ5Mj1UJfLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e421b6f0c210a41cd32df777b1feaf1378c2e5e2d612b1bfe2b93cfa79fddf7","last_reissued_at":"2026-05-18T00:05:38.856054Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:38.856054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Apoorva Sharma, Boris Ivanovic, James Harrison, Marco Pavone, Mo Chen","submitted_at":"2018-06-16T00:59:11Z","abstract_excerpt":"Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation, goal-directed tasks whose natural reward function is sparse remain intractable for state-of-the-art model-free algorithms for continuous control. The bottleneck in these tasks is the prohibitive amount of exploration required to obtain a learning signal from the initial state of the system. In this work, we leverage physical priors in the form of an approximate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06161","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":""},"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":"1806.06161","created_at":"2026-05-18T00:05:38.856171+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06161v2","created_at":"2026-05-18T00:05:38.856171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06161","created_at":"2026-05-18T00:05:38.856171+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZBBW3YMEEFE","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZBBW3YMEEFEDTJS","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZBBW3YM","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E","json":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E.json","graph_json":"https://pith.science/api/pith-number/FZBBW3YMEEFEDTJS353XWH7K6E/graph.json","events_json":"https://pith.science/api/pith-number/FZBBW3YMEEFEDTJS353XWH7K6E/events.json","paper":"https://pith.science/paper/FZBBW3YM"},"agent_actions":{"view_html":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E","download_json":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E.json","view_paper":"https://pith.science/paper/FZBBW3YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06161&json=true","fetch_graph":"https://pith.science/api/pith-number/FZBBW3YMEEFEDTJS353XWH7K6E/graph.json","fetch_events":"https://pith.science/api/pith-number/FZBBW3YMEEFEDTJS353XWH7K6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E/action/storage_attestation","attest_author":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E/action/author_attestation","sign_citation":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E/action/citation_signature","submit_replication":"https://pith.science/pith/FZBBW3YMEEFEDTJS353XWH7K6E/action/replication_record"}},"created_at":"2026-05-18T00:05:38.856171+00:00","updated_at":"2026-05-18T00:05:38.856171+00:00"}