{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QXIXJIAH76JGCVZAQYLXVIQCVX","short_pith_number":"pith:QXIXJIAH","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"},"canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","source":{"kind":"arxiv","id":"1806.03793","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03793","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03793v4","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03793","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"QXIXJIAH76JG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QXIXJIAH76JGCVZA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QXIXJIAH","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QXIXJIAH76JGCVZAQYLXVIQCVX","target":"record","payload":{"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"},"canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","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"},"source_kind":"arxiv","source_id":"1806.03793","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qzhp8kVPgqXiYtkOtL0oQ2M7nMOz1Lq8OfXpJjgWgPTXxHMLaePf25AyuGHq0R5/fdFLzeFOlyHzE5/pw3OzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:18.169340Z"},"content_sha256":"978d373d57ab74fdd950824416d6ed5578f829c18675dd06469d8dbdb515db6e","schema_version":"1.0","event_id":"sha256:978d373d57ab74fdd950824416d6ed5578f829c18675dd06469d8dbdb515db6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QXIXJIAH76JGCVZAQYLXVIQCVX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1oexrYXwoYQW8kbwM/RICb+kkUCgHv/C7rQOpvC+j9FnLcxe0vnoUe7ksXrz1O4xDyoDl+NSMRnJBLi6SeaRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:18.169982Z"},"content_sha256":"87bf43422b651529093999485c3369e3ab36a4442085666d03f9618064ea27be","schema_version":"1.0","event_id":"sha256:87bf43422b651529093999485c3369e3ab36a4442085666d03f9618064ea27be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/bundle.json","state_url":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T15:05:18Z","links":{"resolver":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX","bundle":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/bundle.json","state":"https://pith.science/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXIXJIAH76JGCVZAQYLXVIQCVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QXIXJIAH76JGCVZAQYLXVIQCVX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6d0473b2c744f024886bf85cbb42c5dc7a304b34518c271434fae3b3ad4ecc93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T03:37:43Z","title_canon_sha256":"e5292ca58d15c8a6ec23908b9198025eaf086b158229a3e287c20237dd9ce6c0"},"schema_version":"1.0","source":{"id":"1806.03793","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03793","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03793v4","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03793","created_at":"2026-05-17T23:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"QXIXJIAH76JG","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"QXIXJIAH76JGCVZA","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"QXIXJIAH","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:87bf43422b651529093999485c3369e3ab36a4442085666d03f9618064ea27be","target":"graph","created_at":"2026-05-17T23:51:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chongjie Zhang, Fangda Gu, Guangxiang Zhu, Siyuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T03:37:43Z","title":"Context-Aware Policy Reuse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03793","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:978d373d57ab74fdd950824416d6ed5578f829c18675dd06469d8dbdb515db6e","target":"record","created_at":"2026-05-17T23:51:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6d0473b2c744f024886bf85cbb42c5dc7a304b34518c271434fae3b3ad4ecc93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T03:37:43Z","title_canon_sha256":"e5292ca58d15c8a6ec23908b9198025eaf086b158229a3e287c20237dd9ce6c0"},"schema_version":"1.0","source":{"id":"1806.03793","kind":"arxiv","version":4}},"canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d174a007ff9261572086177aa202adfeba75c50de18c7daafefca7671c834c","first_computed_at":"2026-05-17T23:51:49.325424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:49.325424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y3gxn2VpAbiGmkLCzksv4VzidI83k5RSdvCtbpy76o7HOXXLRZwtY7PplcSDtPnHrkTOTLbojGbLQdceYGO4AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:49.326062Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03793","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:978d373d57ab74fdd950824416d6ed5578f829c18675dd06469d8dbdb515db6e","sha256:87bf43422b651529093999485c3369e3ab36a4442085666d03f9618064ea27be"],"state_sha256":"f3b08c7cc5b1c8d3d82da7f84e8e0220c41c7788e30d1b00c71ae4f55b7d8d3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuTxtq8s9NZNWMzRBVvQJ2ifpMUBE4khYP4Iep8aHLVh6obNpAW6bfzF1cvbtqTVyskkMNZtIpg7GOKy1hkqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:05:18.173651Z","bundle_sha256":"dc93b40ffd187a5debf06e3622a9e0367da663d5e61bae3072d080579bac0501"}}