{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U5V4KUDHD777KZ2U3QCOQOPA3P","short_pith_number":"pith:U5V4KUDH","schema_version":"1.0","canonical_sha256":"a76bc550671ffff56754dc04e839e0dbfe4574c1113c2a6e22072663d489559b","source":{"kind":"arxiv","id":"2110.02639","version":2},"attestation_state":"computed","paper":{"title":"On The Transferability of Deep-Q Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthia Sabatelli, Pierre Geurts","submitted_at":"2021-10-06T10:29:37Z","abstract_excerpt":"Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets. While exploiting TL is a well established and successful training practice in Supervised Learning (SL), its applicability in Deep Reinforcement Learning (DRL) is rarer. In this paper, we study the level of transferability of three different variants of Deep-Q Networks on popular DRL benchmarks as well as on a set of novel, carefully designed control tasks. O"},"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":"2110.02639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T10:29:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"daab21c6d3d9973c835f51cdb92b0ef2d3a87f54f3eac1a07d49c99e924b3b10","abstract_canon_sha256":"49cc40e599c0bff0470b02c88b4f6506637c7ccf240c38c05cc8c94d1d8719c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:07.967430Z","signature_b64":"wZDJpJuOztcnUgnlsYsFKF8wUsTnsEsZiLTKGXOqjiR7FTSQSCW8pLIn+3AQ2U2WlBXkXfuXx+kngG+ABmatAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a76bc550671ffff56754dc04e839e0dbfe4574c1113c2a6e22072663d489559b","last_reissued_at":"2026-07-05T03:34:07.967024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:07.967024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On The Transferability of Deep-Q Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthia Sabatelli, Pierre Geurts","submitted_at":"2021-10-06T10:29:37Z","abstract_excerpt":"Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets. While exploiting TL is a well established and successful training practice in Supervised Learning (SL), its applicability in Deep Reinforcement Learning (DRL) is rarer. In this paper, we study the level of transferability of three different variants of Deep-Q Networks on popular DRL benchmarks as well as on a set of novel, carefully designed control tasks. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02639","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/2110.02639/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":"2110.02639","created_at":"2026-07-05T03:34:07.967082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02639v2","created_at":"2026-07-05T03:34:07.967082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02639","created_at":"2026-07-05T03:34:07.967082+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5V4KUDHD777","created_at":"2026-07-05T03:34:07.967082+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5V4KUDHD777KZ2U","created_at":"2026-07-05T03:34:07.967082+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5V4KUDH","created_at":"2026-07-05T03:34:07.967082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00802","citing_title":"Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P","json":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P.json","graph_json":"https://pith.science/api/pith-number/U5V4KUDHD777KZ2U3QCOQOPA3P/graph.json","events_json":"https://pith.science/api/pith-number/U5V4KUDHD777KZ2U3QCOQOPA3P/events.json","paper":"https://pith.science/paper/U5V4KUDH"},"agent_actions":{"view_html":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P","download_json":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P.json","view_paper":"https://pith.science/paper/U5V4KUDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02639&json=true","fetch_graph":"https://pith.science/api/pith-number/U5V4KUDHD777KZ2U3QCOQOPA3P/graph.json","fetch_events":"https://pith.science/api/pith-number/U5V4KUDHD777KZ2U3QCOQOPA3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P/action/storage_attestation","attest_author":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P/action/author_attestation","sign_citation":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P/action/citation_signature","submit_replication":"https://pith.science/pith/U5V4KUDHD777KZ2U3QCOQOPA3P/action/replication_record"}},"created_at":"2026-07-05T03:34:07.967082+00:00","updated_at":"2026-07-05T03:34:07.967082+00:00"}