{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EQI4NEFDCX634KX5NTHWJYRSAN","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":"3300ade3b5487f4768cf06b3371b0b602c00e9b1a110d67915f6113cc14fd1db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T13:26:26Z","title_canon_sha256":"dc58317bd90119e56ea4bafe4e08d4db3808aff8125a7c3b50c257959abad6f0"},"schema_version":"1.0","source":{"id":"2405.13629","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13629","created_at":"2026-07-05T09:26:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13629v2","created_at":"2026-07-05T09:26:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13629","created_at":"2026-07-05T09:26:26Z"},{"alias_kind":"pith_short_12","alias_value":"EQI4NEFDCX63","created_at":"2026-07-05T09:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"EQI4NEFDCX634KX5","created_at":"2026-07-05T09:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"EQI4NEFD","created_at":"2026-07-05T09:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:2856bce0bff34327f7d086e668d26cc12baf2ba9c774636313b3b53ba2b406b9","target":"graph","created_at":"2026-07-05T09:26:26Z","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/2405.13629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng-Kuang Lee, Chen-Hao Chao, Chien Feng, Chun-Yi Lee, Simon See, Wei-Fang Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T13:26:26Z","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13629","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":"sha256:8348393c7b57c5d989d1da85227d91c648eba6c7016a2ba1b7f4f17b60528e66","target":"record","created_at":"2026-07-05T09:26:26Z","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":"3300ade3b5487f4768cf06b3371b0b602c00e9b1a110d67915f6113cc14fd1db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T13:26:26Z","title_canon_sha256":"dc58317bd90119e56ea4bafe4e08d4db3808aff8125a7c3b50c257959abad6f0"},"schema_version":"1.0","source":{"id":"2405.13629","kind":"arxiv","version":2}},"canonical_sha256":"2411c690a315fdbe2afd6ccf64e232034724eca479eba00964b170e5afdbcf5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2411c690a315fdbe2afd6ccf64e232034724eca479eba00964b170e5afdbcf5d","first_computed_at":"2026-07-05T09:26:26.611230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:26.611230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/SPo9pksch+bJ03igg+Xcjj8qv1dQi1Kz5bATOWjORv/VBvMZwuvxNVLXOQM9AN3g9aVx/dL6iDfXuxiMUygAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:26.611701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13629","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8348393c7b57c5d989d1da85227d91c648eba6c7016a2ba1b7f4f17b60528e66","sha256:2856bce0bff34327f7d086e668d26cc12baf2ba9c774636313b3b53ba2b406b9"],"state_sha256":"d7bf41edd6745dcea21f19aff5aa86b577fe58eeee0abb88a45530fe65f5b6b9"}