{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RCNOO7MWE4TMJXVX7FD7PVQ5GQ","short_pith_number":"pith:RCNOO7MW","schema_version":"1.0","canonical_sha256":"889ae77d962726c4deb7f947f7d61d34059921c77cc59e13d781a33176e4a7f9","source":{"kind":"arxiv","id":"2204.10256","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Abe Friesen, Arunkumar Byravan, Bobak Shahriari, Jost Tobias Springenberg, Martin Riedmiller, Matt Hoffman, Nicolas Heess, Siqi Liu","submitted_at":"2022-04-21T16:44:47Z","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"},"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":"2204.10256","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T16:44:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5aa49a038e9d9d7c38d84ff7b3a77d0ed67a3113343fdda943c31715e601db3","abstract_canon_sha256":"5443917b075870561898bf7d1e48072f52224c00dd91c036ce42e36548a557bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:55.839058Z","signature_b64":"xiZQgiW7IbmbO1f6K0urTIO+pkTjFXlR7nFnMo0Krd7cSeXcXs+gZ70i2NKhOhFUNiIygovvEWC/d+lgbsWPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"889ae77d962726c4deb7f947f7d61d34059921c77cc59e13d781a33176e4a7f9","last_reissued_at":"2026-07-05T04:16:55.838607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:55.838607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Abe Friesen, Arunkumar Byravan, Bobak Shahriari, Jost Tobias Springenberg, Martin Riedmiller, Matt Hoffman, Nicolas Heess, Siqi Liu","submitted_at":"2022-04-21T16:44:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10256","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.10256/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2204.10256","created_at":"2026-07-05T04:16:55.838668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10256v2","created_at":"2026-07-05T04:16:55.838668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10256","created_at":"2026-07-05T04:16:55.838668+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCNOO7MWE4TM","created_at":"2026-07-05T04:16:55.838668+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCNOO7MWE4TMJXVX","created_at":"2026-07-05T04:16:55.838668+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCNOO7MW","created_at":"2026-07-05T04:16:55.838668+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/RCNOO7MWE4TMJXVX7FD7PVQ5GQ","json":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ.json","graph_json":"https://pith.science/api/pith-number/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/graph.json","events_json":"https://pith.science/api/pith-number/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/events.json","paper":"https://pith.science/paper/RCNOO7MW"},"agent_actions":{"view_html":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ","download_json":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ.json","view_paper":"https://pith.science/paper/RCNOO7MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10256&json=true","fetch_graph":"https://pith.science/api/pith-number/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/action/storage_attestation","attest_author":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/action/author_attestation","sign_citation":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/action/citation_signature","submit_replication":"https://pith.science/pith/RCNOO7MWE4TMJXVX7FD7PVQ5GQ/action/replication_record"}},"created_at":"2026-07-05T04:16:55.838668+00:00","updated_at":"2026-07-05T04:16:55.838668+00:00"}