{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HJ2ACN2IFX4BQVU2ERWC3LFJEG","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":"f1a7767c8e29ab38879d1e7149e68d5805568edf53c051dc39e6a402f396b49e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-05T04:22:35Z","title_canon_sha256":"905b40254713e911f9812054c0e64646c2022c7365f06557fee21b8efed74343"},"schema_version":"1.0","source":{"id":"1910.02208","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02208","created_at":"2026-07-05T01:57:13Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02208v4","created_at":"2026-07-05T01:57:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02208","created_at":"2026-07-05T01:57:13Z"},{"alias_kind":"pith_short_12","alias_value":"HJ2ACN2IFX4B","created_at":"2026-07-05T01:57:13Z"},{"alias_kind":"pith_short_16","alias_value":"HJ2ACN2IFX4BQVU2","created_at":"2026-07-05T01:57:13Z"},{"alias_kind":"pith_short_8","alias_value":"HJ2ACN2I","created_at":"2026-07-05T01:57:13Z"}],"graph_snapshots":[{"event_id":"sha256:f7ce461a353a6c4fb9b864ae56c528f8d85cf95e0e12ada81b90d800e9d11365","target":"graph","created_at":"2026-07-05T01:57:13Z","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/1910.02208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entropy term in SAC addresses action saturation due to the bounded nature of the action spaces, with this insight, we propose a streamlined algorithm with a simple normalization scheme or with inverted gradients. We show that both approaches can match SAC's sample efficiency performa","authors_text":"Che Wang, Keith Ross, Quan Vuong, Yanqiu Wu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-05T04:22:35Z","title":"Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02208","kind":"arxiv","version":4},"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:b9670729ec7e395aa128b0e3510ef266d3d95a278dcf08770f89656863cd982a","target":"record","created_at":"2026-07-05T01:57:13Z","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":"f1a7767c8e29ab38879d1e7149e68d5805568edf53c051dc39e6a402f396b49e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-05T04:22:35Z","title_canon_sha256":"905b40254713e911f9812054c0e64646c2022c7365f06557fee21b8efed74343"},"schema_version":"1.0","source":{"id":"1910.02208","kind":"arxiv","version":4}},"canonical_sha256":"3a740137482df818569a246c2daca921b03bd05b44258cbea07a52264797b951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a740137482df818569a246c2daca921b03bd05b44258cbea07a52264797b951","first_computed_at":"2026-07-05T01:57:13.100746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:13.100746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6d+K7aSM7+AtqFylQlnFcBl+9KRQV9jWEw0vyYQsspzz/NDXOrPskt7L75Q5mCPJ57p5XWofxDuygsWmrR7yBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:13.101133Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.02208","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9670729ec7e395aa128b0e3510ef266d3d95a278dcf08770f89656863cd982a","sha256:f7ce461a353a6c4fb9b864ae56c528f8d85cf95e0e12ada81b90d800e9d11365"],"state_sha256":"e4194148bddffd1a91a7a632e8c686d7fb8613e7c9ec0c7f2bdca811f9c6229a"}