{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Q6FGGO6VUCFPCGUPS77756LND7","short_pith_number":"pith:Q6FGGO6V","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"},"canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","source":{"kind":"arxiv","id":"1906.02771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02771","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02771v1","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02771","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q6FGGO6VUCFP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"Q6FGGO6VUCFPCGUP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"Q6FGGO6V","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Q6FGGO6VUCFPCGUPS77756LND7","target":"record","payload":{"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"},"canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","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"},"source_kind":"arxiv","source_id":"1906.02771","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUVhFLTN6mdbMyD5aULMceiCc2CnJ9cVApDWKErlqdzA0OQo8RiOX3BK3cIUvAuFJnLCUVyAoFVyqKM+RbqfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T07:18:39.839978Z"},"content_sha256":"e47c3c03341edcc33fcd52c7a7afefcd238b05290af6660e2d02c9fe6a30c5bd","schema_version":"1.0","event_id":"sha256:e47c3c03341edcc33fcd52c7a7afefcd238b05290af6660e2d02c9fe6a30c5bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Q6FGGO6VUCFPCGUPS77756LND7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zEi32EefbO/Q1W4bkHq6qVCO4mhqep0EKz7ZHT8c6rG/x0ZEzlQdBD1ym3jYrW2wBDOO+a/rfhLDSyEy0GfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T07:18:39.840347Z"},"content_sha256":"47e9e5ab7fb063e5881b7d5e9f6f651866ff0b323d6d04d27ea7304a168ab075","schema_version":"1.0","event_id":"sha256:47e9e5ab7fb063e5881b7d5e9f6f651866ff0b323d6d04d27ea7304a168ab075"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/bundle.json","state_url":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6FGGO6VUCFPCGUPS77756LND7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-20T07:18:39Z","links":{"resolver":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7","bundle":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/bundle.json","state":"https://pith.science/pith/Q6FGGO6VUCFPCGUPS77756LND7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6FGGO6VUCFPCGUPS77756LND7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Q6FGGO6VUCFPCGUPS77756LND7","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":"79fe46120dab514c00d93d955f28fe2332236bcff5aefc667ba2f2d06827938d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T18:43:19Z","title_canon_sha256":"edc20d924f982bc499361ea278b05a7bf287d9e17f87178245a30ea4bc144523"},"schema_version":"1.0","source":{"id":"1906.02771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02771","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02771v1","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02771","created_at":"2026-05-17T23:43:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q6FGGO6VUCFP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"Q6FGGO6VUCFPCGUP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"Q6FGGO6V","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:47e9e5ab7fb063e5881b7d5e9f6f651866ff0b323d6d04d27ea7304a168ab075","target":"graph","created_at":"2026-05-17T23:43:57Z","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"},"paper":{"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","authors_text":"Ariella Smofsky, Avishek Joey Bose, Patrick Nadeem Ward","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T18:43:19Z","title":"Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02771","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:e47c3c03341edcc33fcd52c7a7afefcd238b05290af6660e2d02c9fe6a30c5bd","target":"record","created_at":"2026-05-17T23:43:57Z","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":"79fe46120dab514c00d93d955f28fe2332236bcff5aefc667ba2f2d06827938d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T18:43:19Z","title_canon_sha256":"edc20d924f982bc499361ea278b05a7bf287d9e17f87178245a30ea4bc144523"},"schema_version":"1.0","source":{"id":"1906.02771","kind":"arxiv","version":1}},"canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"878a633bd5a08af11a8f97fffef96d1fc29ace762bd3c59bb6b19503ac620cc8","first_computed_at":"2026-05-17T23:43:57.577378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:57.577378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DKhw/pUiYo74ACcrW/N6Rv2/cXAdKsF0rqc5dHtgXfGmTsDNg6wqAa9QIySdqgzsLey4+WTFV5QTrvfjmm8DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:57.578132Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e47c3c03341edcc33fcd52c7a7afefcd238b05290af6660e2d02c9fe6a30c5bd","sha256:47e9e5ab7fb063e5881b7d5e9f6f651866ff0b323d6d04d27ea7304a168ab075"],"state_sha256":"806127cc414d53952deb639190a08cda4697b969bf579f3a0b5857ebbc94a8d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afzq6p5K4bPtuVNmG1YpFbzNSMri2kpR32AEtxbPlmUtYlk2scdy0wxnI5zsMNCMKO/npRPbdAKjA/dqF3KwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T07:18:39.842322Z","bundle_sha256":"b8b4cf12b4a790bc6fa8e61d7b3b14bdfab7b03830e5ebc6b91b66bc839bde22"}}