{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:76HOQQPDDNLSIFLOA7M7O4ZWV6","short_pith_number":"pith:76HOQQPD","canonical_record":{"source":{"id":"1807.11274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-07-30T10:24:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcdb4af3bce7c5c6f8354a1ace306fd7ca62c6ec02ed9291b92f68240b679142","abstract_canon_sha256":"5c63a49b9887c08520d86fec445cd27ce146e7012a934be45e58663a2b1e3275"},"schema_version":"1.0"},"canonical_sha256":"ff8ee841e31b5724156e07d9f77336af97d6380f7c3d08802cccefd1dbe35461","source":{"kind":"arxiv","id":"1807.11274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11274","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11274v1","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11274","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"76HOQQPDDNLS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"76HOQQPDDNLSIFLO","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"76HOQQPD","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:76HOQQPDDNLSIFLOA7M7O4ZWV6","target":"record","payload":{"canonical_record":{"source":{"id":"1807.11274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-07-30T10:24:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcdb4af3bce7c5c6f8354a1ace306fd7ca62c6ec02ed9291b92f68240b679142","abstract_canon_sha256":"5c63a49b9887c08520d86fec445cd27ce146e7012a934be45e58663a2b1e3275"},"schema_version":"1.0"},"canonical_sha256":"ff8ee841e31b5724156e07d9f77336af97d6380f7c3d08802cccefd1dbe35461","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:32.426627Z","signature_b64":"IIRLgxFXG+5FJY8YWJ6H/8/9YHZSmFCkfyqCXV2rbVUcXjrVfOrpOl3W2KubGEkiB/AzDB/b8HF6JybSBopDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff8ee841e31b5724156e07d9f77336af97d6380f7c3d08802cccefd1dbe35461","last_reissued_at":"2026-05-18T00:09:32.425863Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:32.425863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.11274","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tc28XlQwE9ZHbBI/HA8kjUgxhdtCd3IYwvOV+TgH+eUoErOEG6e52vO5H1mWWsUjLaDeKVBBffev+UfTthtVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:39:14.219688Z"},"content_sha256":"cab7ddd9d36ced1f4f43e510ecb547b4f85b4357246283384807bbe3e350a363","schema_version":"1.0","event_id":"sha256:cab7ddd9d36ced1f4f43e510ecb547b4f85b4357246283384807bbe3e350a363"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:76HOQQPDDNLSIFLOA7M7O4ZWV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Alejandro Ribeiro, Austin Small, Juan Andr\\'es Bazerque, Santiago Paternain","submitted_at":"2018-07-30T10:24:56Z","abstract_excerpt":"Reinforcement learning consists of finding policies that maximize an expected cumulative long-term reward in a Markov decision process with unknown transition probabilities and instantaneous rewards. In this paper, we consider the problem of finding such optimal policies while assuming they are continuous functions belonging to a reproducing kernel Hilbert space (RKHS). To learn the optimal policy we introduce a stochastic policy gradient ascent algorithm with three unique novel features: (i) The stochastic estimates of policy gradients are unbiased. (ii) The variance of stochastic gradients i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11274","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6MrT0vp028SwZAAZN9chuoJgqnv7Q74yjQKfDp5Vu7HiAcJy2+sE/GRWqnbAcfcQE/0yEWc/e+OXrxzSUKxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:39:14.220367Z"},"content_sha256":"ccca19cdc5942091ef9830c615a881a56b1fac23ccf75654873b54b969c5abee","schema_version":"1.0","event_id":"sha256:ccca19cdc5942091ef9830c615a881a56b1fac23ccf75654873b54b969c5abee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/bundle.json","state_url":"https://pith.science/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/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":"2026-06-05T16:39:14Z","links":{"resolver":"https://pith.science/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6","bundle":"https://pith.science/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/bundle.json","state":"https://pith.science/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76HOQQPDDNLSIFLOA7M7O4ZWV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:76HOQQPDDNLSIFLOA7M7O4ZWV6","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":"5c63a49b9887c08520d86fec445cd27ce146e7012a934be45e58663a2b1e3275","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-07-30T10:24:56Z","title_canon_sha256":"fcdb4af3bce7c5c6f8354a1ace306fd7ca62c6ec02ed9291b92f68240b679142"},"schema_version":"1.0","source":{"id":"1807.11274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11274","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11274v1","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11274","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"76HOQQPDDNLS","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"76HOQQPDDNLSIFLO","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"76HOQQPD","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:ccca19cdc5942091ef9830c615a881a56b1fac23ccf75654873b54b969c5abee","target":"graph","created_at":"2026-05-18T00:09:32Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning consists of finding policies that maximize an expected cumulative long-term reward in a Markov decision process with unknown transition probabilities and instantaneous rewards. In this paper, we consider the problem of finding such optimal policies while assuming they are continuous functions belonging to a reproducing kernel Hilbert space (RKHS). To learn the optimal policy we introduce a stochastic policy gradient ascent algorithm with three unique novel features: (i) The stochastic estimates of policy gradients are unbiased. (ii) The variance of stochastic gradients i","authors_text":"Alejandro Ribeiro, Austin Small, Juan Andr\\'es Bazerque, Santiago Paternain","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-07-30T10:24:56Z","title":"Stochastic Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11274","kind":"arxiv","version":1},"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:cab7ddd9d36ced1f4f43e510ecb547b4f85b4357246283384807bbe3e350a363","target":"record","created_at":"2026-05-18T00:09:32Z","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":"5c63a49b9887c08520d86fec445cd27ce146e7012a934be45e58663a2b1e3275","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-07-30T10:24:56Z","title_canon_sha256":"fcdb4af3bce7c5c6f8354a1ace306fd7ca62c6ec02ed9291b92f68240b679142"},"schema_version":"1.0","source":{"id":"1807.11274","kind":"arxiv","version":1}},"canonical_sha256":"ff8ee841e31b5724156e07d9f77336af97d6380f7c3d08802cccefd1dbe35461","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff8ee841e31b5724156e07d9f77336af97d6380f7c3d08802cccefd1dbe35461","first_computed_at":"2026-05-18T00:09:32.425863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:32.425863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIRLgxFXG+5FJY8YWJ6H/8/9YHZSmFCkfyqCXV2rbVUcXjrVfOrpOl3W2KubGEkiB/AzDB/b8HF6JybSBopDCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:32.426627Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cab7ddd9d36ced1f4f43e510ecb547b4f85b4357246283384807bbe3e350a363","sha256:ccca19cdc5942091ef9830c615a881a56b1fac23ccf75654873b54b969c5abee"],"state_sha256":"2d8b7d234bba3f0e79628aa6c08edae8daa10758066c4074142365bb9cd01bad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UsbmRW0k3d8P2OJ3k48cYkCdSn3CiK4dzSDKZlNKu/50pmJtmH2MaeWruEMCoiohUt79CYqdMZ7iPEUeqbiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:39:14.223654Z","bundle_sha256":"4c2d7b3992b880a5b990b86ba6d480ee902b60344d56cad182763533026a1b6d"}}