{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","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":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc"},"schema_version":"1.0","source":{"id":"2411.14913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14913v2","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14913","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"QF3DGSQFE23E","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"QF3DGSQFE23EU4FX","created_at":"2026-07-05T10:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"QF3DGSQF","created_at":"2026-07-05T10:54:14Z"}],"graph_snapshots":[{"event_id":"sha256:0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a","target":"graph","created_at":"2026-07-05T10:54:14Z","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/2411.14913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid framework that tackles both discrete and continuous action spaces. First, we model the continuous motion parameter policy as a diffusion model, and second, we incorporate this into a maximum entropy reinforcement learning framework that unifies both the discrete and continuous components. The discrete action space, such as contact point selection, is optimized thr","authors_text":"Gerhard Neumann, Huy Le, Miroslav Gabriel, Ngo Anh Vien, Tai Hoang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14913","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:c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577","target":"record","created_at":"2026-07-05T10:54:14Z","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":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc"},"schema_version":"1.0","source":{"id":"2411.14913","kind":"arxiv","version":2}},"canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","first_computed_at":"2026-07-05T10:54:14.053307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:14.053307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n3HlAxZspOSS8WnOxLYauRUpdhwblWHeEZ+fQUVHtFx9RQdeJ7GTH9YmIFps1OWpFZEBfzpuYEF1m9Y+IfDfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:14.053810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c45fa31a1aa7ee8adc5a9ff402e5b8afdbf9190cb42e0ef66384a2efdab42577","sha256:0b29b1e6fa2bdf27859bc08ea38e5c131c0d7dfcd361f3b87376bfd124d9567a"],"state_sha256":"cb34e2dbe89e2191394de797cb328ce725a3604c0553ed7b21f0993f632a4bc2"}