{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2EWZTTN6S42Z2JGSFBAXIBWB5Y","short_pith_number":"pith:2EWZTTN6","schema_version":"1.0","canonical_sha256":"d12d99cdbe97359d24d228417406c1ee22e6073da3d415fdac3fe2bd363819a1","source":{"kind":"arxiv","id":"1709.02878","version":2},"attestation_state":"computed","paper":{"title":"TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, James Davidson, Vincent Vanhoucke","submitted_at":"2017-09-08T23:13:01Z","abstract_excerpt":"We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in parallel, and group them to perform the neural network computation on a batch rather than individual observations. This allows the TensorFlow execution engine to parallelize computation, without the need for manual synchronization. Environments are stepped in separate Python processes to progress them in parallel without interference of the global interpreter lock. As part of this project, we introduce BatchPPO, an effi"},"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":"1709.02878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T23:13:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d4305544fa7de67f2c335d6eede1713cc78e2ef39262190aca677e477fcfbd7","abstract_canon_sha256":"d4168f41b3998577ab1e86fc9e7ca72295d28c133b6047aae1527399e9ad4bf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:49.133650Z","signature_b64":"S2PjS8XS833aJe8OTNv75WAa16FfHuas0jLf6fZo1R2IRw0B6ITtsNXOuELzJNQ9H6YMSloFePz33Z8cLKIbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d12d99cdbe97359d24d228417406c1ee22e6073da3d415fdac3fe2bd363819a1","last_reissued_at":"2026-05-18T00:01:49.132995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:49.132995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, James Davidson, Vincent Vanhoucke","submitted_at":"2017-09-08T23:13:01Z","abstract_excerpt":"We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in parallel, and group them to perform the neural network computation on a batch rather than individual observations. This allows the TensorFlow execution engine to parallelize computation, without the need for manual synchronization. Environments are stepped in separate Python processes to progress them in parallel without interference of the global interpreter lock. As part of this project, we introduce BatchPPO, an effi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02878","kind":"arxiv","version":2},"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":"1709.02878","created_at":"2026-05-18T00:01:49.133098+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02878v2","created_at":"2026-05-18T00:01:49.133098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02878","created_at":"2026-05-18T00:01:49.133098+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EWZTTN6S42Z","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EWZTTN6S42Z2JGS","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EWZTTN6","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.19256","citing_title":"HybridFlow: A Flexible and Efficient RLHF Framework","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y","json":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y.json","graph_json":"https://pith.science/api/pith-number/2EWZTTN6S42Z2JGSFBAXIBWB5Y/graph.json","events_json":"https://pith.science/api/pith-number/2EWZTTN6S42Z2JGSFBAXIBWB5Y/events.json","paper":"https://pith.science/paper/2EWZTTN6"},"agent_actions":{"view_html":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y","download_json":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y.json","view_paper":"https://pith.science/paper/2EWZTTN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02878&json=true","fetch_graph":"https://pith.science/api/pith-number/2EWZTTN6S42Z2JGSFBAXIBWB5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2EWZTTN6S42Z2JGSFBAXIBWB5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y/action/storage_attestation","attest_author":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y/action/author_attestation","sign_citation":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y/action/citation_signature","submit_replication":"https://pith.science/pith/2EWZTTN6S42Z2JGSFBAXIBWB5Y/action/replication_record"}},"created_at":"2026-05-18T00:01:49.133098+00:00","updated_at":"2026-05-18T00:01:49.133098+00:00"}