{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TCMMLHA7FOZ2QXXRZ4TFZ77V5Q","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":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6"},"schema_version":"1.0","source":{"id":"2502.02316","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02316v2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02316","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCMMLHA7FOZ2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCMMLHA7FOZ2QXXR","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCMMLHA7","created_at":"2026-07-05T11:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f","target":"graph","created_at":"2026-07-05T11:19:03Z","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/2502.02316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their representational capacity. Diffusion-based policies offer a more expressive alternative, yet integrating them into MaxEnt-RL poses challenges-primarily due to the intractability of computing their marginal entropy. To overcome this, we propose Diffusion-Based Maximum Entropy RL (DIME). \\emph{DIME} leverages recent advances in approximate inference with diff","authors_text":"Daniel Palenicek, Denis Blessing, Ge Li, Georgia Chalvatzaki, Gerhard Neumann, Jan Peters, Onur Celik, Zechu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02316","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":"sha256:1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285","target":"record","created_at":"2026-07-05T11:19:03Z","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":"2cdd74a8144e7b034df2dd0bdd50181693d4c55e54ddecd19f6a19f514e7e5fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T13:37:14Z","title_canon_sha256":"a21b9a2b8edc22978e097b4852bc5012c0ebb2c4fa89bfa92c65a49559e296f6"},"schema_version":"1.0","source":{"id":"2502.02316","kind":"arxiv","version":2}},"canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9898c59c1f2bb3a85ef1cf265cfff5ec14fa9508fa62e9a6829f24c896cbbaec","first_computed_at":"2026-07-05T11:19:03.269813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:03.269813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vjsvglqua2XRYPO/2af7b579iqcKUWK087QfegQs0fl1kM8u9IbKMi6hcpn8vTxKK3tPjzLPxyJ7g8JVGNCICA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:03.270282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02316","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e60b95e6ecbdabfd6a445b8191ccb63b3d7793652f6c871812d0c1b84b28285","sha256:e1f066278989be0ef4511335288265fd82de3cfbc9b45b11603edf5ccb3b019f"],"state_sha256":"2090d6597d9c61b2fc44846cf0314d8fd7c127e2e3d61ec570eb68d1b4993d89"}