{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D6UXPIFLBU7LJRX26H3F5FOPIV","short_pith_number":"pith:D6UXPIFL","schema_version":"1.0","canonical_sha256":"1fa977a0ab0d3eb4c6faf1f65e95cf456856899c5f9866500ae8492883da84f8","source":{"kind":"arxiv","id":"1610.01112","version":2},"attestation_state":"computed","paper":{"title":"Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine, William Montgomery","submitted_at":"2016-10-04T18:05:52Z","abstract_excerpt":"Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human-provided demonstrations, instrumentation of the training environment, or extremely long training times. In this paper, we propose a new reinforcement learning algorithm for learning manipulation skills that can train g"},"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":"1610.01112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-04T18:05:52Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8dcc07b6e761c4c0d7d15d188f684473cbb834bf4056715a894780095244e846","abstract_canon_sha256":"45aa244b7ffd0b73f7e3b6311f3158e8db03d8614f5bd4ee128e7be32636523a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:05.463438Z","signature_b64":"rxiQEsZVK3mWixRtlgtb5qC9jxR4VZ/Jqyachk9vur+KOqOyhydq45qp6oizQUU07Ac4JOmN4clgXIurqv5FBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fa977a0ab0d3eb4c6faf1f65e95cf456856899c5f9866500ae8492883da84f8","last_reissued_at":"2026-05-18T01:03:05.462776Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:05.462776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine, William Montgomery","submitted_at":"2016-10-04T18:05:52Z","abstract_excerpt":"Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to enable practical real-world learning, such as requiring manually designed policy or value function representations, initialization from human-provided demonstrations, instrumentation of the training environment, or extremely long training times. In this paper, we propose a new reinforcement learning algorithm for learning manipulation skills that can train g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01112","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":"1610.01112","created_at":"2026-05-18T01:03:05.462879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.01112v2","created_at":"2026-05-18T01:03:05.462879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01112","created_at":"2026-05-18T01:03:05.462879+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6UXPIFLBU7L","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6UXPIFLBU7LJRX2","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6UXPIFL","created_at":"2026-05-18T12:30:09.641336+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/D6UXPIFLBU7LJRX26H3F5FOPIV","json":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV.json","graph_json":"https://pith.science/api/pith-number/D6UXPIFLBU7LJRX26H3F5FOPIV/graph.json","events_json":"https://pith.science/api/pith-number/D6UXPIFLBU7LJRX26H3F5FOPIV/events.json","paper":"https://pith.science/paper/D6UXPIFL"},"agent_actions":{"view_html":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV","download_json":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV.json","view_paper":"https://pith.science/paper/D6UXPIFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.01112&json=true","fetch_graph":"https://pith.science/api/pith-number/D6UXPIFLBU7LJRX26H3F5FOPIV/graph.json","fetch_events":"https://pith.science/api/pith-number/D6UXPIFLBU7LJRX26H3F5FOPIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV/action/storage_attestation","attest_author":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV/action/author_attestation","sign_citation":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV/action/citation_signature","submit_replication":"https://pith.science/pith/D6UXPIFLBU7LJRX26H3F5FOPIV/action/replication_record"}},"created_at":"2026-05-18T01:03:05.462879+00:00","updated_at":"2026-05-18T01:03:05.462879+00:00"}