{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LTK6NEQ4TWDHPOHRYT6UJSBI3P","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":"80d30eabb40568bd4a2ee1405acf0c55efdc7d4e6b1b76e22b0ec494088f0560","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:18:40Z","title_canon_sha256":"9e0bf28dae4e4fa38e757719f7585f2a8e972fcb231fd05289f9a90579026126"},"schema_version":"1.0","source":{"id":"2404.10645","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10645","created_at":"2026-07-05T08:08:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10645v1","created_at":"2026-07-05T08:08:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10645","created_at":"2026-07-05T08:08:43Z"},{"alias_kind":"pith_short_12","alias_value":"LTK6NEQ4TWDH","created_at":"2026-07-05T08:08:43Z"},{"alias_kind":"pith_short_16","alias_value":"LTK6NEQ4TWDHPOHR","created_at":"2026-07-05T08:08:43Z"},{"alias_kind":"pith_short_8","alias_value":"LTK6NEQ4","created_at":"2026-07-05T08:08:43Z"}],"graph_snapshots":[{"event_id":"sha256:947d3fb79dbd8b523dd9d4b4621753af338a30d67649dfa6f72defa45585e232","target":"graph","created_at":"2026-07-05T08:08:43Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed Distributional DrQ is a model-free and off-policy RL algorithm for continuous control tasks based on the state and observation of the agent, which is an actor-critic method with the data-augmentation and the distributional perspective of critic value function. Aim to learn to control the agent and master some tasks in a high-dimensional continuous space. DrQ-v2 uses DDPG as the backbone and achieves out-performance in various continuous control tasks. Here Distributed Distributional DrQ uses Distributed Distributional DDPG as the backbone, and this modification aims to achieve bett","authors_text":"Zehao Zhou","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:18:40Z","title":"Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10645","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":"sha256:6091c55fb4644b2420b482695de1d79a24eb5c227c4cb43670d470d73bc09f1d","target":"record","created_at":"2026-07-05T08:08:43Z","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":"80d30eabb40568bd4a2ee1405acf0c55efdc7d4e6b1b76e22b0ec494088f0560","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T15:18:40Z","title_canon_sha256":"9e0bf28dae4e4fa38e757719f7585f2a8e972fcb231fd05289f9a90579026126"},"schema_version":"1.0","source":{"id":"2404.10645","kind":"arxiv","version":1}},"canonical_sha256":"5cd5e6921c9d8677b8f1c4fd44c828dbf325ccea0e9b45f4d9bd630408d1c994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cd5e6921c9d8677b8f1c4fd44c828dbf325ccea0e9b45f4d9bd630408d1c994","first_computed_at":"2026-07-05T08:08:43.037061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:43.037061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ONGMFOggMFmixsAP/T/3DlFhRLcdnYkznqReD6kA7JJtw7EEKAVt+Z30/G20mgsrbvSpq5p3WPm2bArfWgFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:43.037442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10645","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6091c55fb4644b2420b482695de1d79a24eb5c227c4cb43670d470d73bc09f1d","sha256:947d3fb79dbd8b523dd9d4b4621753af338a30d67649dfa6f72defa45585e232"],"state_sha256":"292552e86d1bb07031bc668ccc37ea93d0077bf337fc72eb7b6f2c0c561cb5a3"}