{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q5I5NJUIQQZO2DDBCP7YGPRICP","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":"22ebb83b2149ef62ac9f0eb2929b173ca4a850112e655c1f20c090475f1c2eaf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-24T14:18:22Z","title_canon_sha256":"49adc65eb85c76f10a92f0df4718e59b0de71dfacd2dc7c8fad6d2c403bdb044"},"schema_version":"1.0","source":{"id":"2501.14513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14513","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14513v2","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14513","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"Q5I5NJUIQQZO","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"Q5I5NJUIQQZO2DDB","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"Q5I5NJUI","created_at":"2026-07-05T11:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:a337e6e0c1cc06d6dd62bf6ea0fd725cb148f78f58946e1022e946fd2721c5ea","target":"graph","created_at":"2026-07-05T11:06:27Z","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/2501.14513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quadrotor control policies can be trained with high performance using the exact gradients of the rewards to directly optimize policy parameters via backpropagation-through-time (BPTT). However, designing a fully differentiable reward architecture is often challenging. Partially differentiable rewards will result in biased gradient propagation that degrades training performance. To overcome this limitation, we propose Amended Backpropagation-through-Time (ABPT), a novel approach that mitigates gradient bias while preserving the training efficiency of BPTT. ABPT combines 0-step and N-step return","authors_text":"Danping Zou, Fangyu Sun, Fanxing Li, Tianbao Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-24T14:18:22Z","title":"ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14513","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:f30493cdbafaaf6a907e5f19ad729a382e7c74079e3232abc84563619fda04db","target":"record","created_at":"2026-07-05T11:06:27Z","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":"22ebb83b2149ef62ac9f0eb2929b173ca4a850112e655c1f20c090475f1c2eaf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-24T14:18:22Z","title_canon_sha256":"49adc65eb85c76f10a92f0df4718e59b0de71dfacd2dc7c8fad6d2c403bdb044"},"schema_version":"1.0","source":{"id":"2501.14513","kind":"arxiv","version":2}},"canonical_sha256":"8751d6a6888432ed0c6113ff833e2813f2298b74ce62a8a5ea6a3a9abf5f0472","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8751d6a6888432ed0c6113ff833e2813f2298b74ce62a8a5ea6a3a9abf5f0472","first_computed_at":"2026-07-05T11:06:27.223414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:27.223414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNqOdhP8n1oMnKDfcbQlaQZOdZwxFINAso6ZFJqZ/5UrlV7kWs/Yec3QOfDXLhki0co8EWSQfz9Zqmp5aL6eBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:27.223897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f30493cdbafaaf6a907e5f19ad729a382e7c74079e3232abc84563619fda04db","sha256:a337e6e0c1cc06d6dd62bf6ea0fd725cb148f78f58946e1022e946fd2721c5ea"],"state_sha256":"8afeeb983d68a8b38c5e51d4e8aa96dbab25b8d43f8ef9b311c0312f9a8a0206"}