{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DZW7J67UEOPDXPL6I4PZ6O5ZSC","short_pith_number":"pith:DZW7J67U","schema_version":"1.0","canonical_sha256":"1e6df4fbf4239e3bbd7e471f9f3bb990a87b942e487f51cc8ce81b9636e7e5f2","source":{"kind":"arxiv","id":"1712.09381","version":4},"attestation_state":"computed","paper":{"title":"RLlib: Abstractions for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Eric Liang, Ion Stoica, Joseph E. Gonzalez, Ken Goldberg, Michael I. Jordan, Philipp Moritz, Richard Liaw, Robert Nishihara, Roy Fox","submitted_at":"2017-12-26T19:43:59Z","abstract_excerpt":"Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapting algorithms for top-down hierarchical control, thereby encapsulating parallelism and resource requirements within short-running compute tasks. We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL. These primitives enable a broad range of algorithms to be implemented with high pe"},"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":"1712.09381","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-26T19:43:59Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"22a6a037dba228d885cc0658cc837498091109a5ee01a1cca4fc7e688f0c536b","abstract_canon_sha256":"1c296d5881ad88d333552d3d4c715592b1eb54fcf7d45d213f49ff7aa6e91a95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:06.083719Z","signature_b64":"lrGQOnV4ch57QEfPGibAOd5sl7WPEm9qRMUTMvF7tcdN4l22CPmuVkRGov3EnfgGoHZwK0vzMTVIg9ki+mQDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e6df4fbf4239e3bbd7e471f9f3bb990a87b942e487f51cc8ce81b9636e7e5f2","last_reissued_at":"2026-05-18T00:12:06.083079Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:06.083079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLlib: Abstractions for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Eric Liang, Ion Stoica, Joseph E. Gonzalez, Ken Goldberg, Michael I. Jordan, Philipp Moritz, Richard Liaw, Robert Nishihara, Roy Fox","submitted_at":"2017-12-26T19:43:59Z","abstract_excerpt":"Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapting algorithms for top-down hierarchical control, thereby encapsulating parallelism and resource requirements within short-running compute tasks. We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL. These primitives enable a broad range of algorithms to be implemented with high pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09381","kind":"arxiv","version":4},"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":"1712.09381","created_at":"2026-05-18T00:12:06.083172+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09381v4","created_at":"2026-05-18T00:12:06.083172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09381","created_at":"2026-05-18T00:12:06.083172+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZW7J67UEOPD","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZW7J67UEOPDXPL6","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZW7J67U","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2509.07404","citing_title":"Reinforcement learning for adaptive interior point methods in convex quadratic programming","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2509.00338","citing_title":"Scalable Option Learning in High-Throughput Environments","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15432","citing_title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08685","citing_title":"RAMP: Hybrid DRL for Online Learning of Numeric Action Models","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC","json":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC.json","graph_json":"https://pith.science/api/pith-number/DZW7J67UEOPDXPL6I4PZ6O5ZSC/graph.json","events_json":"https://pith.science/api/pith-number/DZW7J67UEOPDXPL6I4PZ6O5ZSC/events.json","paper":"https://pith.science/paper/DZW7J67U"},"agent_actions":{"view_html":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC","download_json":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC.json","view_paper":"https://pith.science/paper/DZW7J67U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09381&json=true","fetch_graph":"https://pith.science/api/pith-number/DZW7J67UEOPDXPL6I4PZ6O5ZSC/graph.json","fetch_events":"https://pith.science/api/pith-number/DZW7J67UEOPDXPL6I4PZ6O5ZSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC/action/storage_attestation","attest_author":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC/action/author_attestation","sign_citation":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC/action/citation_signature","submit_replication":"https://pith.science/pith/DZW7J67UEOPDXPL6I4PZ6O5ZSC/action/replication_record"}},"created_at":"2026-05-18T00:12:06.083172+00:00","updated_at":"2026-05-18T00:12:06.083172+00:00"}