{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:247ZCOIH4ACRXXWF4QLBREBWMN","short_pith_number":"pith:247ZCOIH","schema_version":"1.0","canonical_sha256":"d73f913907e0051bdec5e416189036635d6622dd85e6c2d88b5ddc649244cb47","source":{"kind":"arxiv","id":"2501.16729","version":2},"attestation_state":"computed","paper":{"title":"On the Interplay Between Sparsity and Training in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fatima Davelouis, John D. Martin, Michael Bowling","submitted_at":"2025-01-28T06:13:35Z","abstract_excerpt":"We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned."},"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":"2501.16729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T06:13:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa23cf23e5c72fab8f9b9b0fefd9af50360e58348b9c71d201d6dee900abaf9","abstract_canon_sha256":"8c9d34093fbe410504a931819338119123c3a3f85ae024d0174beed5c8df76d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:28.830214Z","signature_b64":"eDpS9wLcfzpmzP3gPLijDSsQUehOakF/DAf2xL+HZPD3lzUltV5pmawWee8/n8mW3Y6MTL2SQKBs4PrZpT4HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d73f913907e0051bdec5e416189036635d6622dd85e6c2d88b5ddc649244cb47","last_reissued_at":"2026-07-05T10:08:28.829676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:28.829676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Interplay Between Sparsity and Training in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fatima Davelouis, John D. Martin, Michael Bowling","submitted_at":"2025-01-28T06:13:35Z","abstract_excerpt":"We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16729","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.16729/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":"2501.16729","created_at":"2026-07-05T10:08:28.829734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16729v2","created_at":"2026-07-05T10:08:28.829734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16729","created_at":"2026-07-05T10:08:28.829734+00:00"},{"alias_kind":"pith_short_12","alias_value":"247ZCOIH4ACR","created_at":"2026-07-05T10:08:28.829734+00:00"},{"alias_kind":"pith_short_16","alias_value":"247ZCOIH4ACRXXWF","created_at":"2026-07-05T10:08:28.829734+00:00"},{"alias_kind":"pith_short_8","alias_value":"247ZCOIH","created_at":"2026-07-05T10:08:28.829734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN","json":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN.json","graph_json":"https://pith.science/api/pith-number/247ZCOIH4ACRXXWF4QLBREBWMN/graph.json","events_json":"https://pith.science/api/pith-number/247ZCOIH4ACRXXWF4QLBREBWMN/events.json","paper":"https://pith.science/paper/247ZCOIH"},"agent_actions":{"view_html":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN","download_json":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN.json","view_paper":"https://pith.science/paper/247ZCOIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16729&json=true","fetch_graph":"https://pith.science/api/pith-number/247ZCOIH4ACRXXWF4QLBREBWMN/graph.json","fetch_events":"https://pith.science/api/pith-number/247ZCOIH4ACRXXWF4QLBREBWMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN/action/storage_attestation","attest_author":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN/action/author_attestation","sign_citation":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN/action/citation_signature","submit_replication":"https://pith.science/pith/247ZCOIH4ACRXXWF4QLBREBWMN/action/replication_record"}},"created_at":"2026-07-05T10:08:28.829734+00:00","updated_at":"2026-07-05T10:08:28.829734+00:00"}