{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QF3DGSQFE23EU4FX7OMW3VWLJC","short_pith_number":"pith:QF3DGSQF","schema_version":"1.0","canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","source":{"kind":"arxiv","id":"2411.14913","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gerhard Neumann, Huy Le, Miroslav Gabriel, Ngo Anh Vien, Tai Hoang","submitted_at":"2024-11-22T13:14:54Z","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"},"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":"2411.14913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-22T13:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"84ccf9d4634c5d2851466f7b6266234798910cfa5e2d0a7f37c1fc84f7d60dcc","abstract_canon_sha256":"af1590cf7820b29f184bf6de6ec850bc0132bccc3170c78e633cdd19aab496ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:14.053810Z","signature_b64":"n3HlAxZspOSS8WnOxLYauRUpdhwblWHeEZ+fQUVHtFx9RQdeJ7GTH9YmIFps1OWpFZEBfzpuYEF1m9Y+IfDfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8176334a0526b64a70b7fb996dd6cb48bfe31569b65553fb053fbcd5d4cf450c","last_reissued_at":"2026-07-05T10:54:14.053307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:14.053307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gerhard Neumann, Huy Le, Miroslav Gabriel, Ngo Anh Vien, Tai Hoang","submitted_at":"2024-11-22T13:14:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14913","kind":"arxiv","version":2},"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/2411.14913/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":"2411.14913","created_at":"2026-07-05T10:54:14.053374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14913v2","created_at":"2026-07-05T10:54:14.053374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14913","created_at":"2026-07-05T10:54:14.053374+00:00"},{"alias_kind":"pith_short_12","alias_value":"QF3DGSQFE23E","created_at":"2026-07-05T10:54:14.053374+00:00"},{"alias_kind":"pith_short_16","alias_value":"QF3DGSQFE23EU4FX","created_at":"2026-07-05T10:54:14.053374+00:00"},{"alias_kind":"pith_short_8","alias_value":"QF3DGSQF","created_at":"2026-07-05T10:54:14.053374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC","json":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC.json","graph_json":"https://pith.science/api/pith-number/QF3DGSQFE23EU4FX7OMW3VWLJC/graph.json","events_json":"https://pith.science/api/pith-number/QF3DGSQFE23EU4FX7OMW3VWLJC/events.json","paper":"https://pith.science/paper/QF3DGSQF"},"agent_actions":{"view_html":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC","download_json":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC.json","view_paper":"https://pith.science/paper/QF3DGSQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14913&json=true","fetch_graph":"https://pith.science/api/pith-number/QF3DGSQFE23EU4FX7OMW3VWLJC/graph.json","fetch_events":"https://pith.science/api/pith-number/QF3DGSQFE23EU4FX7OMW3VWLJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/action/storage_attestation","attest_author":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/action/author_attestation","sign_citation":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/action/citation_signature","submit_replication":"https://pith.science/pith/QF3DGSQFE23EU4FX7OMW3VWLJC/action/replication_record"}},"created_at":"2026-07-05T10:54:14.053374+00:00","updated_at":"2026-07-05T10:54:14.053374+00:00"}