{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6JKDN33FIIOV5QLUQPHPJJ6WYR","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":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091"},"schema_version":"1.0","source":{"id":"2411.19732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19732v1","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19732","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_12","alias_value":"6JKDN33FIIOV","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_16","alias_value":"6JKDN33FIIOV5QLU","created_at":"2026-07-05T09:42:07Z"},{"alias_kind":"pith_short_8","alias_value":"6JKDN33F","created_at":"2026-07-05T09:42:07Z"}],"graph_snapshots":[{"event_id":"sha256:018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4","target":"graph","created_at":"2026-07-05T09:42:07Z","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/2411.19732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact gradients, they can be unstable in contact-rich environments and may lead to poor generalization. This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms. Our simulation results demonstrate that our method, tested on contact-rich environments, significantly enhances policy robustness ","authors_text":"Eduardo Gonzalez-Sanchez, Gabriele Fadini, Severin Bochem, Yves Bicker","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title":"Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19732","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:e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba","target":"record","created_at":"2026-07-05T09:42:07Z","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":"f4ba79c0b76fe48421bd289f3ef3a5eed746d07b54266c4c904e2e7af5c0a33a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T14:25:54Z","title_canon_sha256":"cbb4d9308f51836fcf55cbb53d38bc4d120c0e0e679dfa521f07c8a12dbf1091"},"schema_version":"1.0","source":{"id":"2411.19732","kind":"arxiv","version":1}},"canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f25436ef65421d5ec17483cef4a7d6c474e44c5304daada05afef0ca505b95e2","first_computed_at":"2026-07-05T09:42:07.450385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:07.450385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bNxL9PnW3PeSulWL673XiSQk3xXE4NiliH8wslt3q74dnCxOwpUjubrsbIuQ+wbJJ+9aoARu9QUOR6MrMaPbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:07.451017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e466ea2e9a95d9e35062324360260fc4c69473da6e88d6eda79b113867fcb3ba","sha256:018b8544f5744a887c8beef1008bafa9bf0df4e8f6d2abc1644d4eac16bc87a4"],"state_sha256":"32eca2473e2416b53c2c11dd83cf4fcd45dbd4491026200417f3be3652e5a7d9"}