{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NSXBVJCV5WOZB6OMW3NRWOAWXD","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":"e1eb27fcfb6d45ef4d96319d59f6029cc1efee437b5fbb45a4178f2fa1bf0eb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T09:55:58Z","title_canon_sha256":"c19cb5a4658112cb978f87aa69357bf020dab8abdf8defb32b2a6d8b5889464c"},"schema_version":"1.0","source":{"id":"2502.11612","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11612","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11612v3","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11612","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"NSXBVJCV5WOZ","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"NSXBVJCV5WOZB6OM","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"NSXBVJCV","created_at":"2026-07-05T11:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:c4c67cc5befb2c903e5318b121cfdf7e32f608117e642b8cbbef2fb2065723e7","target":"graph","created_at":"2026-07-05T11:16:55Z","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/2502.11612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Soft Actor-Critic (SAC) algorithm with a Gaussian policy has become a mainstream implementation for realizing the Maximum Entropy Reinforcement Learning (MaxEnt RL) objective, which incorporates entropy maximization to encourage exploration and enhance policy robustness. While the Gaussian policy performs well on simpler tasks, its exploration capacity and potential performance in complex multi-goal RL environments are limited by its inherent unimodality. In this paper, we employ the diffusion model, a powerful generative model capable of capturing complex multimodal distributions, as the ","authors_text":"Jian Cheng, Xiaoyi Dong, Xi Sheryl Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T09:55:58Z","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11612","kind":"arxiv","version":3},"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":"sha256:9ef1fff3fa775301de6c5100566be8eab9f566c2ec46168239b4f4f0d4033949","target":"record","created_at":"2026-07-05T11:16:55Z","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":"e1eb27fcfb6d45ef4d96319d59f6029cc1efee437b5fbb45a4178f2fa1bf0eb7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T09:55:58Z","title_canon_sha256":"c19cb5a4658112cb978f87aa69357bf020dab8abdf8defb32b2a6d8b5889464c"},"schema_version":"1.0","source":{"id":"2502.11612","kind":"arxiv","version":3}},"canonical_sha256":"6cae1aa455ed9d90f9ccb6db1b3816b8ed6811a018679a840f69e9a6a8a511e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cae1aa455ed9d90f9ccb6db1b3816b8ed6811a018679a840f69e9a6a8a511e4","first_computed_at":"2026-07-05T11:16:55.126260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:55.126260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OjBV1PhjXckLKPEXCj/RrFWwNJUuo8jdNlOcYknHKR/8jCvWbYaoRQOw2mE67SSv3aVremg5lglCJp+/WAe7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:55.126735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11612","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ef1fff3fa775301de6c5100566be8eab9f566c2ec46168239b4f4f0d4033949","sha256:c4c67cc5befb2c903e5318b121cfdf7e32f608117e642b8cbbef2fb2065723e7"],"state_sha256":"05e3962d759173fc78151cdb5384e667642b1b04046c194ce7bad6d11ad50e5c"}