{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QXIXJIAH76JGCVZAQYLXVIQCVX","short_pith_number":"pith:QXIXJIAH","schema_version":"1.0","canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","source":{"kind":"arxiv","id":"1806.03793","version":4},"attestation_state":"computed","paper":{"title":"Context-Aware Policy Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chongjie Zhang, Fangda Gu, Guangxiang Zhu, Siyuan Li","submitted_at":"2018-06-11T03:37:43Z","abstract_excerpt":"Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks.\n  Existing works of policy reuse either focus on only selecting a single best source policy for transfer without considering contexts, or cannot guarantee to learn an optimal policy for a target task.\n  To improve transfer efficiency and guarantee optimality, we develop a novel policy reuse method, called Context-Aware Policy reuSe (CAPS), that enables multi-policy transfer. Our method learns when and which source policy is best for reuse, as well as when to terminate its reus"},"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":"1806.03793","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T03:37:43Z","cross_cats_sorted":[],"title_canon_sha256":"e5292ca58d15c8a6ec23908b9198025eaf086b158229a3e287c20237dd9ce6c0","abstract_canon_sha256":"6d0473b2c744f024886bf85cbb42c5dc7a304b34518c271434fae3b3ad4ecc93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:49.326062Z","signature_b64":"y3gxn2VpAbiGmkLCzksv4VzidI83k5RSdvCtbpy76o7HOXXLRZwtY7PplcSDtPnHrkTOTLbojGbLQdceYGO4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","last_reissued_at":"2026-05-17T23:51:49.325424Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:49.325424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Policy Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chongjie Zhang, Fangda Gu, Guangxiang Zhu, Siyuan Li","submitted_at":"2018-06-11T03:37:43Z","abstract_excerpt":"Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks.\n  Existing works of policy reuse either focus on only selecting a single best source policy for transfer without considering contexts, or cannot guarantee to learn an optimal policy for a target task.\n  To improve transfer efficiency and guarantee optimality, we develop a novel policy reuse method, called Context-Aware Policy reuSe (CAPS), that enables multi-policy transfer. Our method learns when and which source policy is best for reuse, as well as when to terminate its reus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03793","kind":"arxiv","version":4},"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":"1806.03793","created_at":"2026-05-17T23:51:49.325496+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03793v4","created_at":"2026-05-17T23:51:49.325496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03793","created_at":"2026-05-17T23:51:49.325496+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXIXJIAH76JG","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXIXJIAH76JGCVZA","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXIXJIAH","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2312.09436","citing_title":"Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX","json":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX.json","graph_json":"https://pith.science/api/pith-number/QXIXJIAH76JGCVZAQYLXVIQCVX/graph.json","events_json":"https://pith.science/api/pith-number/QXIXJIAH76JGCVZAQYLXVIQCVX/events.json","paper":"https://pith.science/paper/QXIXJIAH"},"agent_actions":{"view_html":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX","download_json":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX.json","view_paper":"https://pith.science/paper/QXIXJIAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03793&json=true","fetch_graph":"https://pith.science/api/pith-number/QXIXJIAH76JGCVZAQYLXVIQCVX/graph.json","fetch_events":"https://pith.science/api/pith-number/QXIXJIAH76JGCVZAQYLXVIQCVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/action/storage_attestation","attest_author":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/action/author_attestation","sign_citation":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/action/citation_signature","submit_replication":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/action/replication_record"}},"created_at":"2026-05-17T23:51:49.325496+00:00","updated_at":"2026-05-17T23:51:49.325496+00:00"}