{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XAOBWPMSTQBUQ74NS3DAERIKMQ","short_pith_number":"pith:XAOBWPMS","canonical_record":{"source":{"id":"2011.11827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T01:18:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c62dc1b6d0701f0ecf58f59b47e60e3cc3baeb5c43c719e5c2f3e788b168c094","abstract_canon_sha256":"b7aac46619300405c969323c2bda59ba6495ecc769a07936f8da8506fd012a3b"},"schema_version":"1.0"},"canonical_sha256":"b81c1b3d929c03487f8d96c602450a642a64bd10714f3752472819449d6f2da6","source":{"kind":"arxiv","id":"2011.11827","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11827","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11827v3","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11827","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"XAOBWPMSTQBU","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"XAOBWPMSTQBUQ74N","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"XAOBWPMS","created_at":"2026-07-05T02:43:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XAOBWPMSTQBUQ74NS3DAERIKMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2011.11827","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T01:18:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c62dc1b6d0701f0ecf58f59b47e60e3cc3baeb5c43c719e5c2f3e788b168c094","abstract_canon_sha256":"b7aac46619300405c969323c2bda59ba6495ecc769a07936f8da8506fd012a3b"},"schema_version":"1.0"},"canonical_sha256":"b81c1b3d929c03487f8d96c602450a642a64bd10714f3752472819449d6f2da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:43:30.948459Z","signature_b64":"nFsmkfZkQiT63FqEQOzJjwzvElySxjYxzKr4jxHftFA5P2ywdlCbhye4jEuJrDyHEBTwVHFOLC5Lp35EE/BjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81c1b3d929c03487f8d96c602450a642a64bd10714f3752472819449d6f2da6","last_reissued_at":"2026-07-05T02:43:30.948057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:43:30.948057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.11827","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cTGBP7S40A2D7E8z+lHOGqdY1drYPDuUYSP+owpdgceqcSNAhAmYvkq+rxvAV3vHGtCn6ZTLV1dlrDR6M5dSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:19:37.626402Z"},"content_sha256":"0e68aaf586708d82dab09165a432974ccfd7f6fb36192a58dd323feccc60e871","schema_version":"1.0","event_id":"sha256:0e68aaf586708d82dab09165a432974ccfd7f6fb36192a58dd323feccc60e871"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XAOBWPMSTQBUQ74NS3DAERIKMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jonathan Chung, Sahika Genc, Sunil Mallya, Tao Sun, Yunzhe Tao","submitted_at":"2020-11-24T01:18:32Z","abstract_excerpt":"Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11827","kind":"arxiv","version":3},"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/2011.11827/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDXxDw/Du8n38tPZ7e0JBy/R8xZSN7CJ1uvErhMhlbuKyGnuDYvGkmsq0mUw/V9MgeVd15CVzINc90rfk0o2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T10:19:37.626785Z"},"content_sha256":"5b7ab19ea495d659d1031aee8880fa0358fb42a6539daa317b12944e2b57fe16","schema_version":"1.0","event_id":"sha256:5b7ab19ea495d659d1031aee8880fa0358fb42a6539daa317b12944e2b57fe16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/bundle.json","state_url":"https://pith.science/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/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":"2026-07-20T10:19:37Z","links":{"resolver":"https://pith.science/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ","bundle":"https://pith.science/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/bundle.json","state":"https://pith.science/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XAOBWPMSTQBUQ74NS3DAERIKMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XAOBWPMSTQBUQ74NS3DAERIKMQ","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":"b7aac46619300405c969323c2bda59ba6495ecc769a07936f8da8506fd012a3b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T01:18:32Z","title_canon_sha256":"c62dc1b6d0701f0ecf58f59b47e60e3cc3baeb5c43c719e5c2f3e788b168c094"},"schema_version":"1.0","source":{"id":"2011.11827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.11827","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2011.11827v3","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11827","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"XAOBWPMSTQBU","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"XAOBWPMSTQBUQ74N","created_at":"2026-07-05T02:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"XAOBWPMS","created_at":"2026-07-05T02:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:5b7ab19ea495d659d1031aee8880fa0358fb42a6539daa317b12944e2b57fe16","target":"graph","created_at":"2026-07-05T02:43:30Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.11827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in","authors_text":"Jonathan Chung, Sahika Genc, Sunil Mallya, Tao Sun, Yunzhe Tao","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T01:18:32Z","title":"REPAINT: Knowledge Transfer in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11827","kind":"arxiv","version":3},"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":"sha256:0e68aaf586708d82dab09165a432974ccfd7f6fb36192a58dd323feccc60e871","target":"record","created_at":"2026-07-05T02:43:30Z","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":"b7aac46619300405c969323c2bda59ba6495ecc769a07936f8da8506fd012a3b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-24T01:18:32Z","title_canon_sha256":"c62dc1b6d0701f0ecf58f59b47e60e3cc3baeb5c43c719e5c2f3e788b168c094"},"schema_version":"1.0","source":{"id":"2011.11827","kind":"arxiv","version":3}},"canonical_sha256":"b81c1b3d929c03487f8d96c602450a642a64bd10714f3752472819449d6f2da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b81c1b3d929c03487f8d96c602450a642a64bd10714f3752472819449d6f2da6","first_computed_at":"2026-07-05T02:43:30.948057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:43:30.948057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nFsmkfZkQiT63FqEQOzJjwzvElySxjYxzKr4jxHftFA5P2ywdlCbhye4jEuJrDyHEBTwVHFOLC5Lp35EE/BjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:43:30.948459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.11827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e68aaf586708d82dab09165a432974ccfd7f6fb36192a58dd323feccc60e871","sha256:5b7ab19ea495d659d1031aee8880fa0358fb42a6539daa317b12944e2b57fe16"],"state_sha256":"4f191c741e6eed36699a7a2d69d7a3a8d25a87cb948f15a36b0cd698c18e5c74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QKnwuqJpSi7/cjboyVvejRvIU4vB0ggW/W2s+aILJPWANP8kmPte5gEuGUmYyuTR7SRLqTmI7aqbjqbxU6IRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T10:19:37.628974Z","bundle_sha256":"14fe58ce3a0c8783de16bdd178f5dbdfa9b987f2dd237f9c46e2170da5c14dab"}}