{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AE725NPEXUMTUDMUITTVBLIIH3","short_pith_number":"pith:AE725NPE","schema_version":"1.0","canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","source":{"kind":"arxiv","id":"1804.08617","version":1},"attestation_state":"computed","paper":{"title":"Distributed Distributional Deterministic Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alistair Muldal, Dan Horgan, David Budden, Dhruva TB, Gabriel Barth-Maron, Matthew W. Hoffman, Nicolas Heess, Timothy Lillicrap, Will Dabney","submitted_at":"2018-04-23T11:57:21Z","abstract_excerpt":"This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we call the Distributed Distributional Deep Deterministic Policy Gradient algorithm, D4PG. We also combine this technique with a number of additional, simple improvements such as the use of $N$-step returns and prioritized experience replay. Experimentally we examine the contribution of each of these individual components, and show how they interact, as well as t"},"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":"1804.08617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T11:57:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"aabc202a803cac1bc2d431aab319235ad81e314119e211430348806f37718942","abstract_canon_sha256":"10558e4324dbeef31402a4ee607700058db3ba36885ffe8b73eb4c155f217ad5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:47.206333Z","signature_b64":"VRWfwoiXxS7xd2C2tevyE7W6Ggm6Eyo16qUp+MolBSfAGWe6S+9828vhnLoqkmbN3D1K+d2fUMPwssW1ZlTcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","last_reissued_at":"2026-05-18T00:17:47.205601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:47.205601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Distributional Deterministic Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alistair Muldal, Dan Horgan, David Budden, Dhruva TB, Gabriel Barth-Maron, Matthew W. Hoffman, Nicolas Heess, Timothy Lillicrap, Will Dabney","submitted_at":"2018-04-23T11:57:21Z","abstract_excerpt":"This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we call the Distributed Distributional Deep Deterministic Policy Gradient algorithm, D4PG. We also combine this technique with a number of additional, simple improvements such as the use of $N$-step returns and prioritized experience replay. Experimentally we examine the contribution of each of these individual components, and show how they interact, as well as t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08617","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":"1804.08617","created_at":"2026-05-18T00:17:47.205712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08617v1","created_at":"2026-05-18T00:17:47.205712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08617","created_at":"2026-05-18T00:17:47.205712+00:00"},{"alias_kind":"pith_short_12","alias_value":"AE725NPEXUMT","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AE725NPEXUMTUDMU","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AE725NPE","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2510.03508","citing_title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11388","citing_title":"Learning to Solve a Rubik's Cube with a Dexterous Hand","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2205.06175","citing_title":"A Generalist Agent","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26481","citing_title":"A Provably Robust Multi-Jet Framework applied to Active Flow Control of an Airfoil in Weakly Compressible Flow","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08253","citing_title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3","json":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3.json","graph_json":"https://pith.science/api/pith-number/AE725NPEXUMTUDMUITTVBLIIH3/graph.json","events_json":"https://pith.science/api/pith-number/AE725NPEXUMTUDMUITTVBLIIH3/events.json","paper":"https://pith.science/paper/AE725NPE"},"agent_actions":{"view_html":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3","download_json":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3.json","view_paper":"https://pith.science/paper/AE725NPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08617&json=true","fetch_graph":"https://pith.science/api/pith-number/AE725NPEXUMTUDMUITTVBLIIH3/graph.json","fetch_events":"https://pith.science/api/pith-number/AE725NPEXUMTUDMUITTVBLIIH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/action/storage_attestation","attest_author":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/action/author_attestation","sign_citation":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/action/citation_signature","submit_replication":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/action/replication_record"}},"created_at":"2026-05-18T00:17:47.205712+00:00","updated_at":"2026-05-18T00:17:47.205712+00:00"}