{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SJZKTPWUVBDWFGJHG4TJXSDZAP","short_pith_number":"pith:SJZKTPWU","schema_version":"1.0","canonical_sha256":"9272a9bed4a84762992737269bc87903e29cb8de855a97dcb142e65c6af9eacf","source":{"kind":"arxiv","id":"1610.00633","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ethan Holly, Sergey Levine, Shixiang Gu, Timothy Lillicrap","submitted_at":"2016-10-03T16:52:10Z","abstract_excerpt":"Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinf"},"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":"1610.00633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-10-03T16:52:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"519b8a4edf8ccabdffaa6299f56c341582480d2689838165791b6f9e9b68dafd","abstract_canon_sha256":"40dad4a9e2e3ac31710fde8d53d88eac2487d29a9a9ec1dd850e98809052c442"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:04.042007Z","signature_b64":"i4tkhVckT0QfW6030tmqCK6PtZnb0UrdKrmpcp+4ePu3iuAm/6FRWPH/tyQQJeuyYlpL7capbQx+CkoE2giFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9272a9bed4a84762992737269bc87903e29cb8de855a97dcb142e65c6af9eacf","last_reissued_at":"2026-05-18T00:57:04.041429Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:04.041429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ethan Holly, Sergey Levine, Shixiang Gu, Timothy Lillicrap","submitted_at":"2016-10-03T16:52:10Z","abstract_excerpt":"Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00633","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":"1610.00633","created_at":"2026-05-18T00:57:04.041519+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.00633v2","created_at":"2026-05-18T00:57:04.041519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00633","created_at":"2026-05-18T00:57:04.041519+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJZKTPWUVBDW","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJZKTPWUVBDWFGJH","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJZKTPWU","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00159","citing_title":"E$^2$DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP","json":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP.json","graph_json":"https://pith.science/api/pith-number/SJZKTPWUVBDWFGJHG4TJXSDZAP/graph.json","events_json":"https://pith.science/api/pith-number/SJZKTPWUVBDWFGJHG4TJXSDZAP/events.json","paper":"https://pith.science/paper/SJZKTPWU"},"agent_actions":{"view_html":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP","download_json":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP.json","view_paper":"https://pith.science/paper/SJZKTPWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/SJZKTPWUVBDWFGJHG4TJXSDZAP/graph.json","fetch_events":"https://pith.science/api/pith-number/SJZKTPWUVBDWFGJHG4TJXSDZAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP/action/storage_attestation","attest_author":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP/action/author_attestation","sign_citation":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP/action/citation_signature","submit_replication":"https://pith.science/pith/SJZKTPWUVBDWFGJHG4TJXSDZAP/action/replication_record"}},"created_at":"2026-05-18T00:57:04.041519+00:00","updated_at":"2026-05-18T00:57:04.041519+00:00"}