{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:D6UXPIFLBU7LJRX26H3F5FOPIV","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":"45aa244b7ffd0b73f7e3b6311f3158e8db03d8614f5bd4ee128e7be32636523a","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-04T18:05:52Z","title_canon_sha256":"8dcc07b6e761c4c0d7d15d188f684473cbb834bf4056715a894780095244e846"},"schema_version":"1.0","source":{"id":"1610.01112","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01112","created_at":"2026-05-18T01:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01112v2","created_at":"2026-05-18T01:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01112","created_at":"2026-05-18T01:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"D6UXPIFLBU7L","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"D6UXPIFLBU7LJRX2","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"D6UXPIFL","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:eb73cfa78cdaac6450b074cad15c13cde5a67426ae38c362490ddd4f785d9cd3","target":"graph","created_at":"2026-05-18T01:03:05Z","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"},"paper":{"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","authors_text":"Anurag Ajay, Chelsea Finn, Pieter Abbeel, Sergey Levine, William Montgomery","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-04T18:05:52Z","title":"Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01112","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":"sha256:410464594e992d48965fc112f00a4a8c2b36f7996ba1c4b2b57baa89ca8b3f61","target":"record","created_at":"2026-05-18T01:03:05Z","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":"45aa244b7ffd0b73f7e3b6311f3158e8db03d8614f5bd4ee128e7be32636523a","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-04T18:05:52Z","title_canon_sha256":"8dcc07b6e761c4c0d7d15d188f684473cbb834bf4056715a894780095244e846"},"schema_version":"1.0","source":{"id":"1610.01112","kind":"arxiv","version":2}},"canonical_sha256":"1fa977a0ab0d3eb4c6faf1f65e95cf456856899c5f9866500ae8492883da84f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fa977a0ab0d3eb4c6faf1f65e95cf456856899c5f9866500ae8492883da84f8","first_computed_at":"2026-05-18T01:03:05.462776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:05.462776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rxiQEsZVK3mWixRtlgtb5qC9jxR4VZ/Jqyachk9vur+KOqOyhydq45qp6oizQUU07Ac4JOmN4clgXIurqv5FBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:05.463438Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01112","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:410464594e992d48965fc112f00a4a8c2b36f7996ba1c4b2b57baa89ca8b3f61","sha256:eb73cfa78cdaac6450b074cad15c13cde5a67426ae38c362490ddd4f785d9cd3"],"state_sha256":"0378a02885f5a13092b3f3cb2de5d5d216afb7449a16e4e3e5550ba335d494ea"}