{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J6F5237MLDIV3HWZRT4SFJWHXB","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":"484e7d62e8a3ef61bffa105f1416c51f7b543a67690b3d8c6476838396ab972d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T07:58:48Z","title_canon_sha256":"0ad3afcaa54f51ce72685fc4b148479e45593c85217cd2f7aa5b6705bb32ca90"},"schema_version":"1.0","source":{"id":"2210.13011","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13011","created_at":"2026-07-05T07:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13011v5","created_at":"2026-07-05T07:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13011","created_at":"2026-07-05T07:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"J6F5237MLDIV","created_at":"2026-07-05T07:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"J6F5237MLDIV3HWZ","created_at":"2026-07-05T07:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"J6F5237M","created_at":"2026-07-05T07:07:05Z"}],"graph_snapshots":[{"event_id":"sha256:cc769df0c235015edc8cd173a2defff2190ace4677322d2ef16e5ced78248bf4","target":"graph","created_at":"2026-07-05T07:07:05Z","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/2210.13011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the variance of stochastic policy gradients (SPGs) with many action samples per state. We derive a many-actions optimality condition, which determines when many-actions SPG yields lower variance as compared to a single-action agent with proportionally extended trajectory. We propose Model-Based Many-Actions (MBMA), an approach leveraging dynamics models for many-actions sampling in the context of SPG. MBMA addresses issues associated with existing implementations of many-actions SPG and yields lower bias and comparable variance to SPG estimated from states in model-simulated rollouts.","authors_text":"Marek Cygan, Michal Nauman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T07:58:48Z","title":"On Many-Actions Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13011","kind":"arxiv","version":5},"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":"sha256:6432e6c6ad757e1035cae7588789d0476cc46cb2653f2151b7dbb1d999d0a711","target":"record","created_at":"2026-07-05T07:07:05Z","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":"484e7d62e8a3ef61bffa105f1416c51f7b543a67690b3d8c6476838396ab972d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T07:58:48Z","title_canon_sha256":"0ad3afcaa54f51ce72685fc4b148479e45593c85217cd2f7aa5b6705bb32ca90"},"schema_version":"1.0","source":{"id":"2210.13011","kind":"arxiv","version":5}},"canonical_sha256":"4f8bdd6fec58d15d9ed98cf922a6c7b8636784f71e90b127c936cc60174324e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f8bdd6fec58d15d9ed98cf922a6c7b8636784f71e90b127c936cc60174324e3","first_computed_at":"2026-07-05T07:07:05.225736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:05.225736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5LT6cJhr+zUPCLK/+V8lL/etEF48IfxF1CWBkWoVGkAvZ8HrWYRldt6SKDO7u+RpSf2V7UN6AP5BBjHJmEnSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:05.226131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13011","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6432e6c6ad757e1035cae7588789d0476cc46cb2653f2151b7dbb1d999d0a711","sha256:cc769df0c235015edc8cd173a2defff2190ace4677322d2ef16e5ced78248bf4"],"state_sha256":"e2cc0b855d25caf8ec1e71e524f7703bfc9e09a000b7a6033dfa567dceea4e7d"}