{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AEU65OP2LKNMQZ77FPXAI5EYEV","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":"def0af243d5d83693306ef2b4d2c3a57afc74c651186ff32bc9eddfad2b0fd5e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-08T16:09:02Z","title_canon_sha256":"4d9d27a8315775a2fa3c11dd3c2ee6bc76374e0f2e7899fda5013dff2397e190"},"schema_version":"1.0","source":{"id":"2202.03957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03957","created_at":"2026-07-05T03:55:22Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03957v1","created_at":"2026-07-05T03:55:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03957","created_at":"2026-07-05T03:55:22Z"},{"alias_kind":"pith_short_12","alias_value":"AEU65OP2LKNM","created_at":"2026-07-05T03:55:22Z"},{"alias_kind":"pith_short_16","alias_value":"AEU65OP2LKNMQZ77","created_at":"2026-07-05T03:55:22Z"},{"alias_kind":"pith_short_8","alias_value":"AEU65OP2","created_at":"2026-07-05T03:55:22Z"}],"graph_snapshots":[{"event_id":"sha256:e427b204205ab25c03c95c34a60f1b16f281a1a182851deb4b363f3827847e48","target":"graph","created_at":"2026-07-05T03:55:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.03957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new policy parameterization for representing 3D rotations during reinforcement learning. Today in the continuous control reinforcement learning literature, many stochastic policy parameterizations are Gaussian. We argue that universally applying a Gaussian policy parameterization is not always desirable for all environments. One such case in particular where this is true are tasks that involve predicting a 3D rotation output, either in isolation, or coupled with translation as part of a full 6D pose output. Our proposed Bingham Policy Parameterization (BPP) models the Bingham dist","authors_text":"Pieter Abbeel, Stephen James","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-08T16:09:02Z","title":"Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03957","kind":"arxiv","version":1},"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":"sha256:17f052866fe255817138488199a2c9ecf17d454efde5ba8417668a44890a70c4","target":"record","created_at":"2026-07-05T03:55:22Z","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":"def0af243d5d83693306ef2b4d2c3a57afc74c651186ff32bc9eddfad2b0fd5e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-08T16:09:02Z","title_canon_sha256":"4d9d27a8315775a2fa3c11dd3c2ee6bc76374e0f2e7899fda5013dff2397e190"},"schema_version":"1.0","source":{"id":"2202.03957","kind":"arxiv","version":1}},"canonical_sha256":"0129eeb9fa5a9ac867ff2bee0474982562dc57c9686f186a239884717814cbd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0129eeb9fa5a9ac867ff2bee0474982562dc57c9686f186a239884717814cbd1","first_computed_at":"2026-07-05T03:55:22.118348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:22.118348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XD3YXuYppc8FEMW+ULfz3sIxOo/ncudUJtT4aP1TMz9lWdOK5gxdjdw4RnoHRtnSbCzDDQj0Htql0G08P4YNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:22.118841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17f052866fe255817138488199a2c9ecf17d454efde5ba8417668a44890a70c4","sha256:e427b204205ab25c03c95c34a60f1b16f281a1a182851deb4b363f3827847e48"],"state_sha256":"7637bb5d33fe5418be972bd90377fc0ff7640863022d71455953879653b337f4"}