{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RCNOO7MWE4TMJXVX7FD7PVQ5GQ","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":"5443917b075870561898bf7d1e48072f52224c00dd91c036ce42e36548a557bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T16:44:47Z","title_canon_sha256":"d5aa49a038e9d9d7c38d84ff7b3a77d0ed67a3113343fdda943c31715e601db3"},"schema_version":"1.0","source":{"id":"2204.10256","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.10256","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2204.10256v2","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10256","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"RCNOO7MWE4TM","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"RCNOO7MWE4TMJXVX","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"RCNOO7MW","created_at":"2026-07-05T04:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:d8cb6715d2a451e388396d8b201969be94633e42ce2b8a1b1c56b666b1c25f2e","target":"graph","created_at":"2026-07-05T04:16:55Z","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/2204.10256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic algorithms that make use of distributional policy evaluation have frequently been shown to outperform their non-distributional counterparts on many challenging control tasks. Examples of this behavior include the D4PG and DMPO algorithms as compared to DDPG and MPO, respectively [Barth-Maron et al., 2018; Hoffman et al., 2020]. However, both agents rely on the C51 critic for value estimation.One major drawback of the C51 approach is its requirement of prior knowledge about the minimum andmaximum values a policy can attain as well as the number of bins used, which fixes the resolut","authors_text":"Abbas Abdolmaleki, Abe Friesen, Arunkumar Byravan, Bobak Shahriari, Jost Tobias Springenberg, Martin Riedmiller, Matt Hoffman, Nicolas Heess, Siqi Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T16:44:47Z","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10256","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":"sha256:6a047d3ca7b7c163bb836cb79a865db13b1627dd0dec7fcf44e0a8b5ab1cb128","target":"record","created_at":"2026-07-05T04:16:55Z","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":"5443917b075870561898bf7d1e48072f52224c00dd91c036ce42e36548a557bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T16:44:47Z","title_canon_sha256":"d5aa49a038e9d9d7c38d84ff7b3a77d0ed67a3113343fdda943c31715e601db3"},"schema_version":"1.0","source":{"id":"2204.10256","kind":"arxiv","version":2}},"canonical_sha256":"889ae77d962726c4deb7f947f7d61d34059921c77cc59e13d781a33176e4a7f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"889ae77d962726c4deb7f947f7d61d34059921c77cc59e13d781a33176e4a7f9","first_computed_at":"2026-07-05T04:16:55.838607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:55.838607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xiZQgiW7IbmbO1f6K0urTIO+pkTjFXlR7nFnMo0Krd7cSeXcXs+gZ70i2NKhOhFUNiIygovvEWC/d+lgbsWPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:55.839058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.10256","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a047d3ca7b7c163bb836cb79a865db13b1627dd0dec7fcf44e0a8b5ab1cb128","sha256:d8cb6715d2a451e388396d8b201969be94633e42ce2b8a1b1c56b666b1c25f2e"],"state_sha256":"d4d98745c392ca8dadfcd06089290e3595e4aee9bc9d5ae7786cc4eb7bd8c86a"}