{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XI74R5BGLPQHH6R5HN533C4KB2","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":"1d851e7a61108cf9b547cda648d764cc13aa7c62b681a6dad8ce0361340213f9","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-30T16:07:51Z","title_canon_sha256":"fa0fe21c1c3e4d8114444aa16e6851a9d6586397173fecf87e0b8bde50b7b647"},"schema_version":"1.0","source":{"id":"1510.09142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.09142","created_at":"2026-05-18T01:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"1510.09142v1","created_at":"2026-05-18T01:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.09142","created_at":"2026-05-18T01:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"XI74R5BGLPQH","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XI74R5BGLPQHH6R5","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XI74R5BG","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:60185f338ce2f21658fa76dca8b9419de64cdc0d23cdb4be465485afba93815a","target":"graph","created_at":"2026-05-18T01:28:22Z","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":"We present a unified framework for learning continuous control policies using backpropagation. It supports stochastic control by treating stochasticity in the Bellman equation as a deterministic function of exogenous noise. The product is a spectrum of general policy gradient algorithms that range from model-free methods with value functions to model-based methods without value functions. We use learned models but only require observations from the environment in- stead of observations from model-predicted trajectories, minimizing the impact of compounded model errors. We apply these algorithm","authors_text":"David Silver, Greg Wayne, Nicolas Heess, Timothy Lillicrap, Tom Erez, Yuval Tassa","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-30T16:07:51Z","title":"Learning Continuous Control Policies by Stochastic Value Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.09142","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:f2b452616679276f3d27fd07cded373f6dbb9a4d990bc39be61444fce00c66f0","target":"record","created_at":"2026-05-18T01:28:22Z","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":"1d851e7a61108cf9b547cda648d764cc13aa7c62b681a6dad8ce0361340213f9","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-30T16:07:51Z","title_canon_sha256":"fa0fe21c1c3e4d8114444aa16e6851a9d6586397173fecf87e0b8bde50b7b647"},"schema_version":"1.0","source":{"id":"1510.09142","kind":"arxiv","version":1}},"canonical_sha256":"ba3fc8f4265be073fa3d3b7bbd8b8a0e80e42f9be36c31de938f0b0cb9638507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba3fc8f4265be073fa3d3b7bbd8b8a0e80e42f9be36c31de938f0b0cb9638507","first_computed_at":"2026-05-18T01:28:22.700279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:28:22.700279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xdy4s82qumw8sMLGNIjGfymfCSxBSIDCUkkT7K2kh0pXjbThAFr4MAlkvugEbD6T9Fj8bbnbRT6OxVr+j/76Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:28:22.701180Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.09142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2b452616679276f3d27fd07cded373f6dbb9a4d990bc39be61444fce00c66f0","sha256:60185f338ce2f21658fa76dca8b9419de64cdc0d23cdb4be465485afba93815a"],"state_sha256":"417d7472fcf2681e055517855c65c009564e5d2eba238eb608bff9037f86c3e2"}