{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PJRPF42HFQAU6QL5D42NXQ7DBB","short_pith_number":"pith:PJRPF42H","schema_version":"1.0","canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","source":{"kind":"arxiv","id":"2106.09776","version":1},"attestation_state":"computed","paper":{"title":"Adapting the Function Approximation Architecture in Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John D. Martin, Joseph Modayil","submitted_at":"2021-06-17T19:33:26Z","abstract_excerpt":"The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm w"},"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":"2106.09776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T19:33:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"072be103b6ba7e29fffec5e1b4319fc02571299feb5be8679034b56ace696033","abstract_canon_sha256":"e8bac2e4e34068b656a168b56f80083f99dcb140907461bb59296fba5fae4ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:20.583342Z","signature_b64":"yYzuodmg/BWYHM516fYRbUnThPM6a/2mUNVEHPQfNW6OX/sElgjshZGvjL9X111/iqj1RVh8z0efS+TEEvFpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a62f2f3472c014f417d1f34dbc3e3087f97f70f048fedaaa75dcebb2f04df3e","last_reissued_at":"2026-07-05T02:50:20.582860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:20.582860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting the Function Approximation Architecture in Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John D. Martin, Joseph Modayil","submitted_at":"2021-06-17T19:33:26Z","abstract_excerpt":"The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09776","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/2106.09776/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":"2106.09776","created_at":"2026-07-05T02:50:20.582918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09776v1","created_at":"2026-07-05T02:50:20.582918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09776","created_at":"2026-07-05T02:50:20.582918+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJRPF42HFQAU","created_at":"2026-07-05T02:50:20.582918+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJRPF42HFQAU6QL5","created_at":"2026-07-05T02:50:20.582918+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJRPF42H","created_at":"2026-07-05T02:50:20.582918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16729","citing_title":"On the Interplay Between Sparsity and Training in Deep Reinforcement Learning","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB","json":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB.json","graph_json":"https://pith.science/api/pith-number/PJRPF42HFQAU6QL5D42NXQ7DBB/graph.json","events_json":"https://pith.science/api/pith-number/PJRPF42HFQAU6QL5D42NXQ7DBB/events.json","paper":"https://pith.science/paper/PJRPF42H"},"agent_actions":{"view_html":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB","download_json":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB.json","view_paper":"https://pith.science/paper/PJRPF42H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09776&json=true","fetch_graph":"https://pith.science/api/pith-number/PJRPF42HFQAU6QL5D42NXQ7DBB/graph.json","fetch_events":"https://pith.science/api/pith-number/PJRPF42HFQAU6QL5D42NXQ7DBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/action/storage_attestation","attest_author":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/action/author_attestation","sign_citation":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/action/citation_signature","submit_replication":"https://pith.science/pith/PJRPF42HFQAU6QL5D42NXQ7DBB/action/replication_record"}},"created_at":"2026-07-05T02:50:20.582918+00:00","updated_at":"2026-07-05T02:50:20.582918+00:00"}