{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SLGM2PBKZ7N4DUSFJE6KET3DVF","short_pith_number":"pith:SLGM2PBK","schema_version":"1.0","canonical_sha256":"92cccd3c2acfdbc1d245493ca24f63a978b09ef156164bc6fa6ccc60f19300b1","source":{"kind":"arxiv","id":"1902.00255","version":2},"attestation_state":"computed","paper":{"title":"Policy Consolidation for Continual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Kaplanis, Claudia Clopath, Murray Shanahan","submitted_at":"2019-02-01T09:59:10Z","abstract_excerpt":"We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \\textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \\textit{continuously} changing environments. In our \\textit{policy consolidation} model, the policy network interacts with a cascade of hidden networks that simultaneously remember the agent's policy at a range of timescales and regularise the current policy by its own history, thereby improving its ability to learn without forgetting. We find that the mod"},"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":"1902.00255","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T09:59:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b5c0e49a9ab3f1475823e91befb999000e138ad07c70f25ce09181cccefa5b3","abstract_canon_sha256":"74a114acf32a0babd791ad7d5dc5585123ef2378f24062480783132332379b5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:16.852345Z","signature_b64":"DTwiPSBLcvfwUeWcuVlaEtbBc53ZH6ndzCZWZmplDMgnZVBKOxlEEl5EjfZVS410t7bwINnUHqoMPnNQnuq/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92cccd3c2acfdbc1d245493ca24f63a978b09ef156164bc6fa6ccc60f19300b1","last_reissued_at":"2026-05-17T23:43:16.851689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:16.851689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Consolidation for Continual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Kaplanis, Claudia Clopath, Murray Shanahan","submitted_at":"2019-02-01T09:59:10Z","abstract_excerpt":"We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \\textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \\textit{continuously} changing environments. In our \\textit{policy consolidation} model, the policy network interacts with a cascade of hidden networks that simultaneously remember the agent's policy at a range of timescales and regularise the current policy by its own history, thereby improving its ability to learn without forgetting. We find that the mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00255","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":""},"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":"1902.00255","created_at":"2026-05-17T23:43:16.851788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00255v2","created_at":"2026-05-17T23:43:16.851788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00255","created_at":"2026-05-17T23:43:16.851788+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLGM2PBKZ7N4","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLGM2PBKZ7N4DUSF","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLGM2PBK","created_at":"2026-05-18T12:33:27.125529+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/SLGM2PBKZ7N4DUSFJE6KET3DVF","json":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF.json","graph_json":"https://pith.science/api/pith-number/SLGM2PBKZ7N4DUSFJE6KET3DVF/graph.json","events_json":"https://pith.science/api/pith-number/SLGM2PBKZ7N4DUSFJE6KET3DVF/events.json","paper":"https://pith.science/paper/SLGM2PBK"},"agent_actions":{"view_html":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF","download_json":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF.json","view_paper":"https://pith.science/paper/SLGM2PBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00255&json=true","fetch_graph":"https://pith.science/api/pith-number/SLGM2PBKZ7N4DUSFJE6KET3DVF/graph.json","fetch_events":"https://pith.science/api/pith-number/SLGM2PBKZ7N4DUSFJE6KET3DVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF/action/storage_attestation","attest_author":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF/action/author_attestation","sign_citation":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF/action/citation_signature","submit_replication":"https://pith.science/pith/SLGM2PBKZ7N4DUSFJE6KET3DVF/action/replication_record"}},"created_at":"2026-05-17T23:43:16.851788+00:00","updated_at":"2026-05-17T23:43:16.851788+00:00"}