{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IXHM65SRDPJGVTIDHHLDFED54X","short_pith_number":"pith:IXHM65SR","schema_version":"1.0","canonical_sha256":"45cecf76511bd26acd0339d632907de5f0b2a936ad4eb2ad35cee451ac1dcfc7","source":{"kind":"arxiv","id":"1803.06773","version":1},"attestation_state":"computed","paper":{"title":"Composable Deep Reinforcement Learning for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurick Zhou, Murtaza Dalal, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja, Vitchyr Pong","submitted_at":"2018-03-19T01:17:16Z","abstract_excerpt":"Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world robotic tasks. In this paper, we study how maximum entropy policies trained using soft Q-learning can be applied to real-world robotic manipulation. The application of this method to real-world manipulation is facilitated by two important features of soft Q-learning. First, soft Q-"},"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":"1803.06773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T01:17:16Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"737bdb76cdc5907806f9635c97c2b6da950b75dcd0117e8cee700d4f04a90a0a","abstract_canon_sha256":"3561db474c7f7481fe81ce538c0b03b4efe0ec50fdc08c6987a9b6a238dabb7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:43.792058Z","signature_b64":"hSGZkQQLb7QMcDuK8OxAcqIeaqtMYcSRMqZRp46sLrjg8i0nfZcmxjcLnW6BuAijQ+l0TBZVxwIGDpojwE/KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45cecf76511bd26acd0339d632907de5f0b2a936ad4eb2ad35cee451ac1dcfc7","last_reissued_at":"2026-05-18T00:20:43.791269Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:43.791269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composable Deep Reinforcement Learning for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurick Zhou, Murtaza Dalal, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja, Vitchyr Pong","submitted_at":"2018-03-19T01:17:16Z","abstract_excerpt":"Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world robotic tasks. In this paper, we study how maximum entropy policies trained using soft Q-learning can be applied to real-world robotic manipulation. The application of this method to real-world manipulation is facilitated by two important features of soft Q-learning. First, soft Q-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06773","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":""},"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":"1803.06773","created_at":"2026-05-18T00:20:43.791410+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06773v1","created_at":"2026-05-18T00:20:43.791410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06773","created_at":"2026-05-18T00:20:43.791410+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXHM65SRDPJG","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXHM65SRDPJGVTID","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXHM65SR","created_at":"2026-05-18T12:32:31.084164+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/IXHM65SRDPJGVTIDHHLDFED54X","json":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X.json","graph_json":"https://pith.science/api/pith-number/IXHM65SRDPJGVTIDHHLDFED54X/graph.json","events_json":"https://pith.science/api/pith-number/IXHM65SRDPJGVTIDHHLDFED54X/events.json","paper":"https://pith.science/paper/IXHM65SR"},"agent_actions":{"view_html":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X","download_json":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X.json","view_paper":"https://pith.science/paper/IXHM65SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06773&json=true","fetch_graph":"https://pith.science/api/pith-number/IXHM65SRDPJGVTIDHHLDFED54X/graph.json","fetch_events":"https://pith.science/api/pith-number/IXHM65SRDPJGVTIDHHLDFED54X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X/action/storage_attestation","attest_author":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X/action/author_attestation","sign_citation":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X/action/citation_signature","submit_replication":"https://pith.science/pith/IXHM65SRDPJGVTIDHHLDFED54X/action/replication_record"}},"created_at":"2026-05-18T00:20:43.791410+00:00","updated_at":"2026-05-18T00:20:43.791410+00:00"}