{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AEU65OP2LKNMQZ77FPXAI5EYEV","short_pith_number":"pith:AEU65OP2","schema_version":"1.0","canonical_sha256":"0129eeb9fa5a9ac867ff2bee0474982562dc57c9686f186a239884717814cbd1","source":{"kind":"arxiv","id":"2202.03957","version":1},"attestation_state":"computed","paper":{"title":"Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Pieter Abbeel, Stephen James","submitted_at":"2022-02-08T16:09:02Z","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"},"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":"2202.03957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-08T16:09:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"4d9d27a8315775a2fa3c11dd3c2ee6bc76374e0f2e7899fda5013dff2397e190","abstract_canon_sha256":"def0af243d5d83693306ef2b4d2c3a57afc74c651186ff32bc9eddfad2b0fd5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:22.118841Z","signature_b64":"XD3YXuYppc8FEMW+ULfz3sIxOo/ncudUJtT4aP1TMz9lWdOK5gxdjdw4RnoHRtnSbCzDDQj0Htql0G08P4YNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0129eeb9fa5a9ac867ff2bee0474982562dc57c9686f186a239884717814cbd1","last_reissued_at":"2026-07-05T03:55:22.118348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:22.118348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Pieter Abbeel, Stephen James","submitted_at":"2022-02-08T16:09:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03957","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.03957/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2202.03957","created_at":"2026-07-05T03:55:22.118413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03957v1","created_at":"2026-07-05T03:55:22.118413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03957","created_at":"2026-07-05T03:55:22.118413+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEU65OP2LKNM","created_at":"2026-07-05T03:55:22.118413+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEU65OP2LKNMQZ77","created_at":"2026-07-05T03:55:22.118413+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEU65OP2","created_at":"2026-07-05T03:55:22.118413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07588","citing_title":"Information-Geometric Optimization on Spheres","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV","json":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV.json","graph_json":"https://pith.science/api/pith-number/AEU65OP2LKNMQZ77FPXAI5EYEV/graph.json","events_json":"https://pith.science/api/pith-number/AEU65OP2LKNMQZ77FPXAI5EYEV/events.json","paper":"https://pith.science/paper/AEU65OP2"},"agent_actions":{"view_html":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV","download_json":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV.json","view_paper":"https://pith.science/paper/AEU65OP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03957&json=true","fetch_graph":"https://pith.science/api/pith-number/AEU65OP2LKNMQZ77FPXAI5EYEV/graph.json","fetch_events":"https://pith.science/api/pith-number/AEU65OP2LKNMQZ77FPXAI5EYEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV/action/storage_attestation","attest_author":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV/action/author_attestation","sign_citation":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV/action/citation_signature","submit_replication":"https://pith.science/pith/AEU65OP2LKNMQZ77FPXAI5EYEV/action/replication_record"}},"created_at":"2026-07-05T03:55:22.118413+00:00","updated_at":"2026-07-05T03:55:22.118413+00:00"}