{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q6FGGO6VUCFPCGUPS77756LND7","short_pith_number":"pith:Q6FGGO6V","schema_version":"1.0","canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","source":{"kind":"arxiv","id":"1906.02771","version":1},"attestation_state":"computed","paper":{"title":"Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ariella Smofsky, Avishek Joey Bose, Patrick Nadeem Ward","submitted_at":"2019-06-06T18:43:19Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \\cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm within the maximum entropy RL framework which offers greater stability and empirical gains. The choice of policy distribution, a factored Gaussian, is motivated by \\cut{chosen due}its easy re-parametrization rather than its modeling power. We introduce Normalizing Flow policies within the SAC framework that learn more expressive classes of policies than simple"},"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":"1906.02771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T18:43:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"edc20d924f982bc499361ea278b05a7bf287d9e17f87178245a30ea4bc144523","abstract_canon_sha256":"79fe46120dab514c00d93d955f28fe2332236bcff5aefc667ba2f2d06827938d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:57.578132Z","signature_b64":"1DKhw/pUiYo74ACcrW/N6Rv2/cXAdKsF0rqc5dHtgXfGmTsDNg6wqAa9QIySdqgzsLey4+WTFV5QTrvfjmm8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","last_reissued_at":"2026-05-17T23:43:57.577378Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:57.577378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ariella Smofsky, Avishek Joey Bose, Patrick Nadeem Ward","submitted_at":"2019-06-06T18:43:19Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \\cut{being}sample inefficient. Soft Actor Critic (SAC) proposes an off-policy deep actor critic algorithm within the maximum entropy RL framework which offers greater stability and empirical gains. The choice of policy distribution, a factored Gaussian, is motivated by \\cut{chosen due}its easy re-parametrization rather than its modeling power. We introduce Normalizing Flow policies within the SAC framework that learn more expressive classes of policies than simple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02771","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.02771","created_at":"2026-05-17T23:43:57.577512+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02771v1","created_at":"2026-05-17T23:43:57.577512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02771","created_at":"2026-05-17T23:43:57.577512+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6FGGO6VUCFP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6FGGO6VUCFPCGUP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6FGGO6V","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7","json":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7.json","graph_json":"https://pith.science/api/pith-number/Q6FGGO6VUCFPCGUPS77756LND7/graph.json","events_json":"https://pith.science/api/pith-number/Q6FGGO6VUCFPCGUPS77756LND7/events.json","paper":"https://pith.science/paper/Q6FGGO6V"},"agent_actions":{"view_html":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7","download_json":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7.json","view_paper":"https://pith.science/paper/Q6FGGO6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02771&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6FGGO6VUCFPCGUPS77756LND7/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6FGGO6VUCFPCGUPS77756LND7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/action/storage_attestation","attest_author":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/action/author_attestation","sign_citation":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/action/citation_signature","submit_replication":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/action/replication_record"}},"created_at":"2026-05-17T23:43:57.577512+00:00","updated_at":"2026-05-17T23:43:57.577512+00:00"}