{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AE725NPEXUMTUDMUITTVBLIIH3","short_pith_number":"pith:AE725NPE","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"},"canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","source":{"kind":"arxiv","id":"1804.08617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08617","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08617v1","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08617","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"AE725NPEXUMT","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AE725NPEXUMTUDMU","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AE725NPE","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AE725NPEXUMTUDMUITTVBLIIH3","target":"record","payload":{"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"},"canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","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"},"source_kind":"arxiv","source_id":"1804.08617","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":"2026-05-18T00:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"og5ze1zIVcRQo73VNaI9jbTOXOvCLtdghXC+pEjGt6R0PMlGdtuCZ9Bb9JZwllbBf4vlOzwyeki1SSBcDv8/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:26:24.045982Z"},"content_sha256":"2daef225878dcd119374f0c1b1149eb3f9658a5df22db6cc67a1a6deaa220bc4","schema_version":"1.0","event_id":"sha256:2daef225878dcd119374f0c1b1149eb3f9658a5df22db6cc67a1a6deaa220bc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AE725NPEXUMTUDMUITTVBLIIH3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEVL2m91uWFQf7CdK4QsHIU+46woUECZejKBWhFnGRFbL+GzOgzX7CBuFcBy1BvEYdNAdBMY4gwh97X1NEEaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:26:24.046412Z"},"content_sha256":"37af0e15315e06b572ea5ddcb1414ad5e9098fb8ca7e02f4e203511269363040","schema_version":"1.0","event_id":"sha256:37af0e15315e06b572ea5ddcb1414ad5e9098fb8ca7e02f4e203511269363040"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/bundle.json","state_url":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AE725NPEXUMTUDMUITTVBLIIH3/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":"2026-05-30T06:26:24Z","links":{"resolver":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3","bundle":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/bundle.json","state":"https://pith.science/pith/AE725NPEXUMTUDMUITTVBLIIH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AE725NPEXUMTUDMUITTVBLIIH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AE725NPEXUMTUDMUITTVBLIIH3","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":"10558e4324dbeef31402a4ee607700058db3ba36885ffe8b73eb4c155f217ad5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T11:57:21Z","title_canon_sha256":"aabc202a803cac1bc2d431aab319235ad81e314119e211430348806f37718942"},"schema_version":"1.0","source":{"id":"1804.08617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08617","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08617v1","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08617","created_at":"2026-05-18T00:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"AE725NPEXUMT","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AE725NPEXUMTUDMU","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AE725NPE","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:37af0e15315e06b572ea5ddcb1414ad5e9098fb8ca7e02f4e203511269363040","target":"graph","created_at":"2026-05-18T00:17:47Z","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":"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","authors_text":"Alistair Muldal, Dan Horgan, David Budden, Dhruva TB, Gabriel Barth-Maron, Matthew W. Hoffman, Nicolas Heess, Timothy Lillicrap, Will Dabney","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T11:57:21Z","title":"Distributed Distributional Deterministic Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08617","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":"sha256:2daef225878dcd119374f0c1b1149eb3f9658a5df22db6cc67a1a6deaa220bc4","target":"record","created_at":"2026-05-18T00:17:47Z","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":"10558e4324dbeef31402a4ee607700058db3ba36885ffe8b73eb4c155f217ad5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T11:57:21Z","title_canon_sha256":"aabc202a803cac1bc2d431aab319235ad81e314119e211430348806f37718942"},"schema_version":"1.0","source":{"id":"1804.08617","kind":"arxiv","version":1}},"canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"013faeb5e4bd193a0d9444e750ad083ed4b6b566d1ff7f50ca9eb1e202b3e35e","first_computed_at":"2026-05-18T00:17:47.205601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:47.205601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VRWfwoiXxS7xd2C2tevyE7W6Ggm6Eyo16qUp+MolBSfAGWe6S+9828vhnLoqkmbN3D1K+d2fUMPwssW1ZlTcBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:47.206333Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2daef225878dcd119374f0c1b1149eb3f9658a5df22db6cc67a1a6deaa220bc4","sha256:37af0e15315e06b572ea5ddcb1414ad5e9098fb8ca7e02f4e203511269363040"],"state_sha256":"12d0c46eaf1bc93cb02cb6985d2c7b536274ee20184880ff95a8130fcfaebcf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3LoSCtMCZzQWDzAuTl779xEA+RSHlzxJmaL9q+z/x0fSzrakmBNsIWZDv0/1xVQpWDMMdufPKgwj8GQ13H2pAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:26:24.048343Z","bundle_sha256":"6c240db5acf1e5c5643401f82591051db701a184ae7a1c2f4542955f73f10fa2"}}