{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","short_pith_number":"pith:DXDJP5J6","schema_version":"1.0","canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","source":{"kind":"arxiv","id":"1811.12927","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Navdeep Jaitly, Nevena Lazic, Reza Mahjourian, Risto Miikkulainen, Sergey Levine","submitted_at":"2018-11-30T18:27:41Z","abstract_excerpt":"Training robots with physical bodies requires developing new methods and action representations that allow the learning agents to explore the space of policies efficiently. This work studies sample-efficient learning of complex policies in the context of robot table tennis. It incorporates learning into a hierarchical control framework using a model-free strategy layer (which requires complex reasoning about opponents that is difficult to do in a model-based way), model-based prediction of external objects (which are difficult to control directly with analytic control methods, but governed by "},"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":"1811.12927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","cross_cats_sorted":[],"title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849","abstract_canon_sha256":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.006389Z","signature_b64":"+Ebrmy1+PWnO8ROdcPnhn9f9RBqayQqNh8AJVBWon1VzeC6CNqvHtHXKZCEZ5nxVUo5LElUEMTkpZHBECuxEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","last_reissued_at":"2026-05-17T23:53:50.005712Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.005712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Navdeep Jaitly, Nevena Lazic, Reza Mahjourian, Risto Miikkulainen, Sergey Levine","submitted_at":"2018-11-30T18:27:41Z","abstract_excerpt":"Training robots with physical bodies requires developing new methods and action representations that allow the learning agents to explore the space of policies efficiently. This work studies sample-efficient learning of complex policies in the context of robot table tennis. It incorporates learning into a hierarchical control framework using a model-free strategy layer (which requires complex reasoning about opponents that is difficult to do in a model-based way), model-based prediction of external objects (which are difficult to control directly with analytic control methods, but governed by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12927","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":"1811.12927","created_at":"2026-05-17T23:53:50.005845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12927v2","created_at":"2026-05-17T23:53:50.005845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12927","created_at":"2026-05-17T23:53:50.005845+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXDJP5J6OPIO","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXDJP5J6OPIOSTAN","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXDJP5J6","created_at":"2026-05-18T12:32:19.392346+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/DXDJP5J6OPIOSTANBTJR7RHBB4","json":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4.json","graph_json":"https://pith.science/api/pith-number/DXDJP5J6OPIOSTANBTJR7RHBB4/graph.json","events_json":"https://pith.science/api/pith-number/DXDJP5J6OPIOSTANBTJR7RHBB4/events.json","paper":"https://pith.science/paper/DXDJP5J6"},"agent_actions":{"view_html":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4","download_json":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4.json","view_paper":"https://pith.science/paper/DXDJP5J6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12927&json=true","fetch_graph":"https://pith.science/api/pith-number/DXDJP5J6OPIOSTANBTJR7RHBB4/graph.json","fetch_events":"https://pith.science/api/pith-number/DXDJP5J6OPIOSTANBTJR7RHBB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/action/storage_attestation","attest_author":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/action/author_attestation","sign_citation":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/action/citation_signature","submit_replication":"https://pith.science/pith/DXDJP5J6OPIOSTANBTJR7RHBB4/action/replication_record"}},"created_at":"2026-05-17T23:53:50.005845+00:00","updated_at":"2026-05-17T23:53:50.005845+00:00"}