{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XI74R5BGLPQHH6R5HN533C4KB2","short_pith_number":"pith:XI74R5BG","schema_version":"1.0","canonical_sha256":"ba3fc8f4265be073fa3d3b7bbd8b8a0e80e42f9be36c31de938f0b0cb9638507","source":{"kind":"arxiv","id":"1510.09142","version":1},"attestation_state":"computed","paper":{"title":"Learning Continuous Control Policies by Stochastic Value Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"David Silver, Greg Wayne, Nicolas Heess, Timothy Lillicrap, Tom Erez, Yuval Tassa","submitted_at":"2015-10-30T16:07:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1510.09142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-30T16:07:51Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"fa0fe21c1c3e4d8114444aa16e6851a9d6586397173fecf87e0b8bde50b7b647","abstract_canon_sha256":"1d851e7a61108cf9b547cda648d764cc13aa7c62b681a6dad8ce0361340213f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:22.701180Z","signature_b64":"xdy4s82qumw8sMLGNIjGfymfCSxBSIDCUkkT7K2kh0pXjbThAFr4MAlkvugEbD6T9Fj8bbnbRT6OxVr+j/76Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba3fc8f4265be073fa3d3b7bbd8b8a0e80e42f9be36c31de938f0b0cb9638507","last_reissued_at":"2026-05-18T01:28:22.700279Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:22.700279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Continuous Control Policies by Stochastic Value Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"David Silver, Greg Wayne, Nicolas Heess, Timothy Lillicrap, Tom Erez, Yuval Tassa","submitted_at":"2015-10-30T16:07:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.09142","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1510.09142","created_at":"2026-05-18T01:28:22.700420+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.09142v1","created_at":"2026-05-18T01:28:22.700420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.09142","created_at":"2026-05-18T01:28:22.700420+00:00"},{"alias_kind":"pith_short_12","alias_value":"XI74R5BGLPQH","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XI74R5BGLPQHH6R5","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XI74R5BG","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19029","citing_title":"Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1506.02438","citing_title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2","json":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2.json","graph_json":"https://pith.science/api/pith-number/XI74R5BGLPQHH6R5HN533C4KB2/graph.json","events_json":"https://pith.science/api/pith-number/XI74R5BGLPQHH6R5HN533C4KB2/events.json","paper":"https://pith.science/paper/XI74R5BG"},"agent_actions":{"view_html":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2","download_json":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2.json","view_paper":"https://pith.science/paper/XI74R5BG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.09142&json=true","fetch_graph":"https://pith.science/api/pith-number/XI74R5BGLPQHH6R5HN533C4KB2/graph.json","fetch_events":"https://pith.science/api/pith-number/XI74R5BGLPQHH6R5HN533C4KB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2/action/storage_attestation","attest_author":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2/action/author_attestation","sign_citation":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2/action/citation_signature","submit_replication":"https://pith.science/pith/XI74R5BGLPQHH6R5HN533C4KB2/action/replication_record"}},"created_at":"2026-05-18T01:28:22.700420+00:00","updated_at":"2026-05-18T01:28:22.700420+00:00"}