{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2M4SWOJVPQHLPDY5CVOZ55KQTM","short_pith_number":"pith:2M4SWOJV","canonical_record":{"source":{"id":"2505.23244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T08:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"737f307dba97b1a9c86041f44b8de6d1b645d8adc06f5eb5b0c1324d561159ef","abstract_canon_sha256":"dc9de14db70edea9ca9ccbcc6fa181444a0303c17049864bd1cb0767b8f71976"},"schema_version":"1.0"},"canonical_sha256":"d3392b39357c0eb78f1d155d9ef5509b0197c0bc7aa191da8cd622dfed4ca867","source":{"kind":"arxiv","id":"2505.23244","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23244","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23244v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23244","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"2M4SWOJVPQHL","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"2M4SWOJVPQHLPDY5","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"2M4SWOJV","created_at":"2026-07-05T11:18:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2M4SWOJVPQHLPDY5CVOZ55KQTM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T08:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"737f307dba97b1a9c86041f44b8de6d1b645d8adc06f5eb5b0c1324d561159ef","abstract_canon_sha256":"dc9de14db70edea9ca9ccbcc6fa181444a0303c17049864bd1cb0767b8f71976"},"schema_version":"1.0"},"canonical_sha256":"d3392b39357c0eb78f1d155d9ef5509b0197c0bc7aa191da8cd622dfed4ca867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:43.333192Z","signature_b64":"D/qFwFWfc+R0tzXjrs1wIlUKoXBUpej3iXJ999pmrdxct6de8ZAaJ0QlzfITKiLrB3pkUw/s5DWqXLahAfdrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3392b39357c0eb78f1d155d9ef5509b0197c0bc7aa191da8cd622dfed4ca867","last_reissued_at":"2026-07-05T11:18:43.332711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:43.332711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23244","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1pkVwp5s1oXCU0lrx23NfuNvxN5ZwlI9FZWTwDGupf33ly/K2Uxczyv1e2r/+s+A7L90j+TJDToXpZqWn8tJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:59:21.429239Z"},"content_sha256":"b93d00c088fde1c660ae035be10c0ed2d73b201d6a2b81252738daef96ec75fa","schema_version":"1.0","event_id":"sha256:b93d00c088fde1c660ae035be10c0ed2d73b201d6a2b81252738daef96ec75fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2M4SWOJVPQHLPDY5CVOZ55KQTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Equivalence of stochastic and deterministic policy gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emo Todorov","submitted_at":"2025-05-29T08:51:34Z","abstract_excerpt":"Policy gradients in continuous control have been derived for both stochastic and deterministic policies. Here we study the relationship between the two. In a widely-used family of MDPs involving Gaussian control noise and quadratic control costs, we show that the stochastic and deterministic policy gradients, natural gradients, and state value functions are identical; while the state-control value functions are different. We then develop a general procedure for constructing an MDP with deterministic policy that is equivalent to a given MDP with stochastic policy. The controls of this new MDP a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23244","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/2505.23244/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTmtIVAB1Vun14ukrHdguldBSgnQ3f1u0gR+UtKBXYFbGAEKtjiGa0qJAbQ2WdSiVL+P2gpli27z0peeB8aDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:59:21.429645Z"},"content_sha256":"4c30639788739b82c94807cdfc5fcf65e8825d470ea7ca99360c2cacfe1b34f1","schema_version":"1.0","event_id":"sha256:4c30639788739b82c94807cdfc5fcf65e8825d470ea7ca99360c2cacfe1b34f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/bundle.json","state_url":"https://pith.science/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:59:21Z","links":{"resolver":"https://pith.science/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM","bundle":"https://pith.science/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/bundle.json","state":"https://pith.science/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2M4SWOJVPQHLPDY5CVOZ55KQTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2M4SWOJVPQHLPDY5CVOZ55KQTM","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":"dc9de14db70edea9ca9ccbcc6fa181444a0303c17049864bd1cb0767b8f71976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T08:51:34Z","title_canon_sha256":"737f307dba97b1a9c86041f44b8de6d1b645d8adc06f5eb5b0c1324d561159ef"},"schema_version":"1.0","source":{"id":"2505.23244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23244","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23244v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23244","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"2M4SWOJVPQHL","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"2M4SWOJVPQHLPDY5","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"2M4SWOJV","created_at":"2026-07-05T11:18:43Z"}],"graph_snapshots":[{"event_id":"sha256:4c30639788739b82c94807cdfc5fcf65e8825d470ea7ca99360c2cacfe1b34f1","target":"graph","created_at":"2026-07-05T11:18:43Z","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/2505.23244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradients in continuous control have been derived for both stochastic and deterministic policies. Here we study the relationship between the two. In a widely-used family of MDPs involving Gaussian control noise and quadratic control costs, we show that the stochastic and deterministic policy gradients, natural gradients, and state value functions are identical; while the state-control value functions are different. We then develop a general procedure for constructing an MDP with deterministic policy that is equivalent to a given MDP with stochastic policy. The controls of this new MDP a","authors_text":"Emo Todorov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T08:51:34Z","title":"Equivalence of stochastic and deterministic policy gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23244","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:b93d00c088fde1c660ae035be10c0ed2d73b201d6a2b81252738daef96ec75fa","target":"record","created_at":"2026-07-05T11:18:43Z","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":"dc9de14db70edea9ca9ccbcc6fa181444a0303c17049864bd1cb0767b8f71976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T08:51:34Z","title_canon_sha256":"737f307dba97b1a9c86041f44b8de6d1b645d8adc06f5eb5b0c1324d561159ef"},"schema_version":"1.0","source":{"id":"2505.23244","kind":"arxiv","version":2}},"canonical_sha256":"d3392b39357c0eb78f1d155d9ef5509b0197c0bc7aa191da8cd622dfed4ca867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3392b39357c0eb78f1d155d9ef5509b0197c0bc7aa191da8cd622dfed4ca867","first_computed_at":"2026-07-05T11:18:43.332711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:43.332711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/qFwFWfc+R0tzXjrs1wIlUKoXBUpej3iXJ999pmrdxct6de8ZAaJ0QlzfITKiLrB3pkUw/s5DWqXLahAfdrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:43.333192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b93d00c088fde1c660ae035be10c0ed2d73b201d6a2b81252738daef96ec75fa","sha256:4c30639788739b82c94807cdfc5fcf65e8825d470ea7ca99360c2cacfe1b34f1"],"state_sha256":"1d113ad8bc982c8957bf60e2d8aa1f110f3c71560f852986669a4834597a64a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WiUd/dFEnJSlKTKVDqpW5DegmaRkAY97qL1iUG4vatbwU6A3yErMZaonIl2PJFycjUsJCv+3n7/xsL95flTcCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:59:21.432849Z","bundle_sha256":"eec949dcc59acb65f07ae291f02b0b63d9ea8644ab6d39adfff9052f45436937"}}