{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KNMWXFX2VTKC7ID7SPD4P6GUYV","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":"5f56e5ab32f3710b0f25e7a41cd18411adf3db4761ba2b139bcc54bb7a48f0e4","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-25T13:28:16Z","title_canon_sha256":"980166acc8817ea8e056c2d9165d78304628f4eab0c581b88552ecf6c00bdb5b"},"schema_version":"1.0","source":{"id":"2011.12719","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.12719","created_at":"2026-07-05T03:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"2011.12719v4","created_at":"2026-07-05T03:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12719","created_at":"2026-07-05T03:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"KNMWXFX2VTKC","created_at":"2026-07-05T03:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"KNMWXFX2VTKC7ID7","created_at":"2026-07-05T03:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"KNMWXFX2","created_at":"2026-07-05T03:26:57Z"}],"graph_snapshots":[{"event_id":"sha256:f89b996faf9b4247a126d2f8d086c5ea4faa87b10dcec9295079496fd5dba25e","target":"graph","created_at":"2026-07-05T03:26:57Z","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/2011.12719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years. In this paper, we re-examine the challenges posed by distributed RL and try to view it through the lens of an old idea: distributed dataflow. We show that viewing RL as a dataflow problem leads to highly composable and performant implementations. We propose RLlib Flow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms i","authors_text":"Eric Liang, Ion Stoica, Joseph E. Gonzalez, Michael Luo, Sven Mika, Zhanghao Wu","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-25T13:28:16Z","title":"RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12719","kind":"arxiv","version":4},"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:c3f6a38c8ef41520e5b5ed9feab669b363fab4e33debaf56d35debe11421b416","target":"record","created_at":"2026-07-05T03:26:57Z","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":"5f56e5ab32f3710b0f25e7a41cd18411adf3db4761ba2b139bcc54bb7a48f0e4","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-25T13:28:16Z","title_canon_sha256":"980166acc8817ea8e056c2d9165d78304628f4eab0c581b88552ecf6c00bdb5b"},"schema_version":"1.0","source":{"id":"2011.12719","kind":"arxiv","version":4}},"canonical_sha256":"53596b96faacd42fa07f93c7c7f8d4c5675dbd938cfa5bf9825439b6323610e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53596b96faacd42fa07f93c7c7f8d4c5675dbd938cfa5bf9825439b6323610e5","first_computed_at":"2026-07-05T03:26:57.968742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:57.968742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VZlHcnc7NS1nd7Koh3bt4w+9gV3k13xwi0s+r1vd+7ggPnp4VKPKlDxX3pUYwtlrxs3WbyBkUQjQL6Yq2zo0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:57.969271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.12719","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3f6a38c8ef41520e5b5ed9feab669b363fab4e33debaf56d35debe11421b416","sha256:f89b996faf9b4247a126d2f8d086c5ea4faa87b10dcec9295079496fd5dba25e"],"state_sha256":"0c227900b5efe23eeae8d596d824f1ee6cf53d66293cb82a7aa3806ae6e14192"}