{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RHBJQ5EMUGGTI7NYOYB6M4NTYF","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":"2d8bf9eb79da3a0db469b2f94fc8d2dd329baf9b21ca83810fc158ed92ce8b07","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-10T11:59:59Z","title_canon_sha256":"d3c2316b02c4a10b5b10b84e718aa13ca42b0edce673f0ffc489c8f62a96a516"},"schema_version":"1.0","source":{"id":"1801.03326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.03326","created_at":"2026-07-05T00:59:50Z"},{"alias_kind":"arxiv_version","alias_value":"1801.03326v2","created_at":"2026-07-05T00:59:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03326","created_at":"2026-07-05T00:59:50Z"},{"alias_kind":"pith_short_12","alias_value":"RHBJQ5EMUGGT","created_at":"2026-07-05T00:59:50Z"},{"alias_kind":"pith_short_16","alias_value":"RHBJQ5EMUGGTI7NY","created_at":"2026-07-05T00:59:50Z"},{"alias_kind":"pith_short_8","alias_value":"RHBJQ5EM","created_at":"2026-07-05T00:59:50Z"}],"graph_snapshots":[{"event_id":"sha256:22e51d5d1adb867ba5109e2bfe54ad467b2a88612b117399de2dd594e638d2a9","target":"graph","created_at":"2026-07-05T00:59:50Z","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/1801.03326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory. For continuous action spaces, we first derive a practical result for Gaussian policies and quadratic critics and then extend it to a universal analytical method, covering a broad class of actors and critics, including Gaussian, exponential families, and policies with bounded su","authors_text":"Kamil Ciosek, Shimon Whiteson","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-10T11:59:59Z","title":"Expected Policy Gradients for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03326","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":"sha256:780324f690bddb6d8cc95aafc38a7cde13b15a7c30a06d668389d564944d6786","target":"record","created_at":"2026-07-05T00:59:50Z","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":"2d8bf9eb79da3a0db469b2f94fc8d2dd329baf9b21ca83810fc158ed92ce8b07","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-10T11:59:59Z","title_canon_sha256":"d3c2316b02c4a10b5b10b84e718aa13ca42b0edce673f0ffc489c8f62a96a516"},"schema_version":"1.0","source":{"id":"1801.03326","kind":"arxiv","version":2}},"canonical_sha256":"89c298748ca18d347db87603e671b3c17f9b49c870387eaa0190a8ceebcb7c4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c298748ca18d347db87603e671b3c17f9b49c870387eaa0190a8ceebcb7c4f","first_computed_at":"2026-07-05T00:59:50.991973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:50.991973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ttaJvZukEHGAXeEUlEII9RwOtp8sRxoF49OC62esMwaygjGLVBUNkq2+7fP/OHJzx4xb4h+TEt3BvIL9hOi2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:50.992408Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.03326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:780324f690bddb6d8cc95aafc38a7cde13b15a7c30a06d668389d564944d6786","sha256:22e51d5d1adb867ba5109e2bfe54ad467b2a88612b117399de2dd594e638d2a9"],"state_sha256":"cf8969ea79f6b6699b1ee4a9c719323452a998183a7e89d8c791513c66e94ad1"}