{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NOR3RKEX24VKEEP6BUZLVBKCJW","short_pith_number":"pith:NOR3RKEX","schema_version":"1.0","canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","source":{"kind":"arxiv","id":"2104.01655","version":1},"attestation_state":"computed","paper":{"title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov","submitted_at":"2021-04-04T17:56:34Z","abstract_excerpt":"Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These \"actor-latency\" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within "},"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":"2104.01655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T17:56:34Z","cross_cats_sorted":[],"title_canon_sha256":"ee6c060ac714c012232e04819620e63c7f8c391d1efc17cbd111d3b35360c0bf","abstract_canon_sha256":"d452a5dd6231572054bb270cdd34538686c11c12799f163b5b1d4ef0b8d26f1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:02.310227Z","signature_b64":"38E6s6odMlqv0D/BnPguKHryNID0W1IF0atRU+8yYUZf0f1bAR777IXr0pjq4oUhjLgs7d65OdwrD4I4j3IJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba3b8a897d72aa211fe0d32ba85424db085ed9fcf8eb6665569609ed2ce9786","last_reissued_at":"2026-07-05T02:29:02.309865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:02.309865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov","submitted_at":"2021-04-04T17:56:34Z","abstract_excerpt":"Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These \"actor-latency\" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01655","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.01655/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.01655","created_at":"2026-07-05T02:29:02.309920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01655v1","created_at":"2026-07-05T02:29:02.309920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01655","created_at":"2026-07-05T02:29:02.309920+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOR3RKEX24VK","created_at":"2026-07-05T02:29:02.309920+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOR3RKEX24VKEEP6","created_at":"2026-07-05T02:29:02.309920+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOR3RKEX","created_at":"2026-07-05T02:29:02.309920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21956","citing_title":"Optimal Return-to-Go Guided Decision Transformer for Auto-Bidding in Advertisement","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW","json":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW.json","graph_json":"https://pith.science/api/pith-number/NOR3RKEX24VKEEP6BUZLVBKCJW/graph.json","events_json":"https://pith.science/api/pith-number/NOR3RKEX24VKEEP6BUZLVBKCJW/events.json","paper":"https://pith.science/paper/NOR3RKEX"},"agent_actions":{"view_html":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW","download_json":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW.json","view_paper":"https://pith.science/paper/NOR3RKEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01655&json=true","fetch_graph":"https://pith.science/api/pith-number/NOR3RKEX24VKEEP6BUZLVBKCJW/graph.json","fetch_events":"https://pith.science/api/pith-number/NOR3RKEX24VKEEP6BUZLVBKCJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/action/storage_attestation","attest_author":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/action/author_attestation","sign_citation":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/action/citation_signature","submit_replication":"https://pith.science/pith/NOR3RKEX24VKEEP6BUZLVBKCJW/action/replication_record"}},"created_at":"2026-07-05T02:29:02.309920+00:00","updated_at":"2026-07-05T02:29:02.309920+00:00"}