{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EQI4NEFDCX634KX5NTHWJYRSAN","short_pith_number":"pith:EQI4NEFD","schema_version":"1.0","canonical_sha256":"2411c690a315fdbe2afd6ccf64e232034724eca479eba00964b170e5afdbcf5d","source":{"kind":"arxiv","id":"2405.13629","version":2},"attestation_state":"computed","paper":{"title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng-Kuang Lee, Chen-Hao Chao, Chien Feng, Chun-Yi Lee, Simon See, Wei-Fang Sun","submitted_at":"2024-05-22T13:26:26Z","abstract_excerpt":"Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy improvement. In the policy evaluation steps, the critic is updated to capture the soft Q-function. In the policy improvement steps, the actor is adjusted in accordance with the updated soft Q-function. In this paper, we introduce a new MaxEnt RL framework modeled using Energy-Based Normalizing Flows (EBFlow). This framework integrates the policy evaluation steps and th"},"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":"2405.13629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T13:26:26Z","cross_cats_sorted":[],"title_canon_sha256":"dc58317bd90119e56ea4bafe4e08d4db3808aff8125a7c3b50c257959abad6f0","abstract_canon_sha256":"3300ade3b5487f4768cf06b3371b0b602c00e9b1a110d67915f6113cc14fd1db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:26.611701Z","signature_b64":"/SPo9pksch+bJ03igg+Xcjj8qv1dQi1Kz5bATOWjORv/VBvMZwuvxNVLXOQM9AN3g9aVx/dL6iDfXuxiMUygAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2411c690a315fdbe2afd6ccf64e232034724eca479eba00964b170e5afdbcf5d","last_reissued_at":"2026-07-05T09:26:26.611230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:26.611230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng-Kuang Lee, Chen-Hao Chao, Chien Feng, Chun-Yi Lee, Simon See, Wei-Fang Sun","submitted_at":"2024-05-22T13:26:26Z","abstract_excerpt":"Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy improvement. In the policy evaluation steps, the critic is updated to capture the soft Q-function. In the policy improvement steps, the actor is adjusted in accordance with the updated soft Q-function. In this paper, we introduce a new MaxEnt RL framework modeled using Energy-Based Normalizing Flows (EBFlow). This framework integrates the policy evaluation steps and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13629","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/2405.13629/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":"2405.13629","created_at":"2026-07-05T09:26:26.611286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13629v2","created_at":"2026-07-05T09:26:26.611286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13629","created_at":"2026-07-05T09:26:26.611286+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQI4NEFDCX63","created_at":"2026-07-05T09:26:26.611286+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQI4NEFDCX634KX5","created_at":"2026-07-05T09:26:26.611286+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQI4NEFD","created_at":"2026-07-05T09:26:26.611286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06967","citing_title":"GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19771","citing_title":"Frictional Q-Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN","json":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN.json","graph_json":"https://pith.science/api/pith-number/EQI4NEFDCX634KX5NTHWJYRSAN/graph.json","events_json":"https://pith.science/api/pith-number/EQI4NEFDCX634KX5NTHWJYRSAN/events.json","paper":"https://pith.science/paper/EQI4NEFD"},"agent_actions":{"view_html":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN","download_json":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN.json","view_paper":"https://pith.science/paper/EQI4NEFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13629&json=true","fetch_graph":"https://pith.science/api/pith-number/EQI4NEFDCX634KX5NTHWJYRSAN/graph.json","fetch_events":"https://pith.science/api/pith-number/EQI4NEFDCX634KX5NTHWJYRSAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN/action/storage_attestation","attest_author":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN/action/author_attestation","sign_citation":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN/action/citation_signature","submit_replication":"https://pith.science/pith/EQI4NEFDCX634KX5NTHWJYRSAN/action/replication_record"}},"created_at":"2026-07-05T09:26:26.611286+00:00","updated_at":"2026-07-05T09:26:26.611286+00:00"}