{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7CDRWVVI7ZNHK6RB2ZELKZZ7TK","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":"625930b9f3b19901cd17a98b62f2e53c42c6a1f849ff51b22ad1f442114cc7ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T15:23:41Z","title_canon_sha256":"46e5937315570c298ba02481855946bb1f0c770be826ab280ff9f34fdd9c593f"},"schema_version":"1.0","source":{"id":"2305.13122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13122","created_at":"2026-07-05T06:12:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13122v1","created_at":"2026-07-05T06:12:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13122","created_at":"2026-07-05T06:12:26Z"},{"alias_kind":"pith_short_12","alias_value":"7CDRWVVI7ZNH","created_at":"2026-07-05T06:12:26Z"},{"alias_kind":"pith_short_16","alias_value":"7CDRWVVI7ZNHK6RB","created_at":"2026-07-05T06:12:26Z"},{"alias_kind":"pith_short_8","alias_value":"7CDRWVVI","created_at":"2026-07-05T06:12:26Z"}],"graph_snapshots":[{"event_id":"sha256:cd5403a2b25ff8501a0ec105a211788cf927015a4a11f629d4763dc5a7eef0f2","target":"graph","created_at":"2026-07-05T06:12:26Z","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/2305.13122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Popular reinforcement learning (RL) algorithms tend to produce a unimodal policy distribution, which weakens the expressiveness of complicated policy and decays the ability of exploration. The diffusion probability model is powerful to learn complicated multimodal distributions, which has shown promising and potential applications to RL. In this paper, we formally build a theoretical foundation of policy representation via the diffusion probability model and provide practical implementations of diffusion policy for online model-free RL. Concretely, we character diffusion policy as a stochastic","authors_text":"Binbin Zhou, Cong Fang, Fenghao Lei, Long Yang, Shiting Wen, Yiming Yang, Yucun Zhong, Zhixiong Huang, Zhouchen Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T15:23:41Z","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13122","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":"sha256:4fa3da26730b58c2177ef2b81c5cfa79706dfb630a0acd2405d3520bfea7193d","target":"record","created_at":"2026-07-05T06:12:26Z","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":"625930b9f3b19901cd17a98b62f2e53c42c6a1f849ff51b22ad1f442114cc7ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-22T15:23:41Z","title_canon_sha256":"46e5937315570c298ba02481855946bb1f0c770be826ab280ff9f34fdd9c593f"},"schema_version":"1.0","source":{"id":"2305.13122","kind":"arxiv","version":1}},"canonical_sha256":"f8871b56a8fe5a757a21d648b5673f9a95ddb03bb226f2358bfc5b0efc88931d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8871b56a8fe5a757a21d648b5673f9a95ddb03bb226f2358bfc5b0efc88931d","first_computed_at":"2026-07-05T06:12:26.617950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:26.617950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qd2a6tLaWB2F2Z2BcEfhQMOx+SzhKlkSqfs6g2yRXW1+DIp1lieh+M7gbDL39nDP/+8PQ1q8hgFMOX7y2eOuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:26.618453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fa3da26730b58c2177ef2b81c5cfa79706dfb630a0acd2405d3520bfea7193d","sha256:cd5403a2b25ff8501a0ec105a211788cf927015a4a11f629d4763dc5a7eef0f2"],"state_sha256":"68850940071890c506d3864b8f032389e765418fd45f941f93e63d2adf9c2ebc"}