{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DXDJP5J6OPIOSTANBTJR7RHBB4","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":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849"},"schema_version":"1.0","source":{"id":"1811.12927","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1811.12927v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12927","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"DXDJP5J6OPIO","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DXDJP5J6OPIOSTAN","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DXDJP5J6","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79","target":"graph","created_at":"2026-05-17T23:53:50Z","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":"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 ","authors_text":"Navdeep Jaitly, Nevena Lazic, Reza Mahjourian, Risto Miikkulainen, Sergey Levine","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title":"Hierarchical Policy Design for Sample-Efficient Learning of Robot Table Tennis Through Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12927","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:acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7","target":"record","created_at":"2026-05-17T23:53:50Z","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":"3014cd829780ed02b8e7262a1d63039f17a551e992ada9ba4ca02045da4142a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-11-30T18:27:41Z","title_canon_sha256":"4a40307f16be99a1c9b3de96eaa656e9d073923d6e2f6169acb7fd5087aec849"},"schema_version":"1.0","source":{"id":"1811.12927","kind":"arxiv","version":2}},"canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dc697f53e73d0e94c0d0cd31fc4e10f2f04f66cb73c1f86facc21f6561e807e","first_computed_at":"2026-05-17T23:53:50.005712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:50.005712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Ebrmy1+PWnO8ROdcPnhn9f9RBqayQqNh8AJVBWon1VzeC6CNqvHtHXKZCEZ5nxVUo5LElUEMTkpZHBECuxEAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:50.006389Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.12927","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acc6710ee755f8c992fbbd378763d99f0efb1cb07385d8aa4284c92676ca1fa7","sha256:90ad5fc44330df121b54be6d92987bed120f8188ec8d92dba6ab73582c09dd79"],"state_sha256":"c60d4588600e9cede343464f83bf6ee6c56aa418247fad17b03eb0ed3b59badd"}