{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OLCKF2737DLXFJ3TT55DCOUIH","short_pith_number":"pith:3OLCKF27","schema_version":"1.0","canonical_sha256":"db9625175fdfc6bb953b9cfbd189d441c4035dca115c78213737654b47f84891","source":{"kind":"arxiv","id":"2305.15555","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Plasticity Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Clare Lyle, Evgenii Nikishin, Georg Ostrovski, Junhyuk Oh, Razvan Pascanu, Will Dabney","submitted_at":"2023-05-24T20:41:35Z","abstract_excerpt":"A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered by the complex relationship between plasticity, exploration, and performance in RL. This paper introduces plasticity injection, a minimalistic intervention that increases the network plasticity without changing the number of trainable parameters or biasing the predictions. The applications of this intervention are two-fold: first, as a diagnostic tool $\\unico"},"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":"2305.15555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T20:41:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc11469158885c2b16f26133626f6d49ddfb7efc2a68eb1c48997f7b78aa4b42","abstract_canon_sha256":"e589ee084a44f7ab27f8ca4d4c396bdd564dd32fa644ec1b49b86fd875d09a33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:53.510256Z","signature_b64":"rnwM+vKbfo8DiA4tjKcKDUL4YgKIMGT1cRN/hrHI/VSYQqD/+LDLk2dIBUaOG2NToOW0a0mGRbxwzpAss2jDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db9625175fdfc6bb953b9cfbd189d441c4035dca115c78213737654b47f84891","last_reissued_at":"2026-07-05T06:56:53.509761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:53.509761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Plasticity Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Clare Lyle, Evgenii Nikishin, Georg Ostrovski, Junhyuk Oh, Razvan Pascanu, Will Dabney","submitted_at":"2023-05-24T20:41:35Z","abstract_excerpt":"A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered by the complex relationship between plasticity, exploration, and performance in RL. This paper introduces plasticity injection, a minimalistic intervention that increases the network plasticity without changing the number of trainable parameters or biasing the predictions. The applications of this intervention are two-fold: first, as a diagnostic tool $\\unico"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15555","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/2305.15555/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":"2305.15555","created_at":"2026-07-05T06:56:53.509828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15555v2","created_at":"2026-07-05T06:56:53.509828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15555","created_at":"2026-07-05T06:56:53.509828+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OLCKF2737DL","created_at":"2026-07-05T06:56:53.509828+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OLCKF2737DLXFJ3","created_at":"2026-07-05T06:56:53.509828+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OLCKF27","created_at":"2026-07-05T06:56:53.509828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02712","citing_title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH","json":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH.json","graph_json":"https://pith.science/api/pith-number/3OLCKF2737DLXFJ3TT55DCOUIH/graph.json","events_json":"https://pith.science/api/pith-number/3OLCKF2737DLXFJ3TT55DCOUIH/events.json","paper":"https://pith.science/paper/3OLCKF27"},"agent_actions":{"view_html":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH","download_json":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH.json","view_paper":"https://pith.science/paper/3OLCKF27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15555&json=true","fetch_graph":"https://pith.science/api/pith-number/3OLCKF2737DLXFJ3TT55DCOUIH/graph.json","fetch_events":"https://pith.science/api/pith-number/3OLCKF2737DLXFJ3TT55DCOUIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH/action/storage_attestation","attest_author":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH/action/author_attestation","sign_citation":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH/action/citation_signature","submit_replication":"https://pith.science/pith/3OLCKF2737DLXFJ3TT55DCOUIH/action/replication_record"}},"created_at":"2026-07-05T06:56:53.509828+00:00","updated_at":"2026-07-05T06:56:53.509828+00:00"}