{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NPXG26NONTZMMBTILRZ3EY6KWU","short_pith_number":"pith:NPXG26NO","canonical_record":{"source":{"id":"1901.08277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa2ca1e5118de87056e5ffae21af3e7079a173583dbbc0356cd0f6c1f723730","abstract_canon_sha256":"e9ad04da246cd2bd9ce8a12c7074f479d74e10440b951b03d1839a9029254f90"},"schema_version":"1.0"},"canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","source":{"kind":"arxiv","id":"1901.08277","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08277","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08277v3","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08277","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"NPXG26NONTZM","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_16","alias_value":"NPXG26NONTZMMBTI","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_8","alias_value":"NPXG26NO","created_at":"2026-07-05T00:39:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NPXG26NONTZMMBTILRZ3EY6KWU","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa2ca1e5118de87056e5ffae21af3e7079a173583dbbc0356cd0f6c1f723730","abstract_canon_sha256":"e9ad04da246cd2bd9ce8a12c7074f479d74e10440b951b03d1839a9029254f90"},"schema_version":"1.0"},"canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:10.069805Z","signature_b64":"zX5wbMXsg/7dQ8G0Im2yKCfj7g9NWXHxVIStX9UG51DN8ybpV+Eytmy3FmaaDwxEIOXgNGpo41RJMpI40NOxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","last_reissued_at":"2026-07-05T00:39:10.069373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:10.069373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08277","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":"2026-07-05T00:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hhMTkIgojYlIGc+BdBNwVOyKNdDe6glk93ScfDueCNGjB9N/FGTjyp9qcyXwyqyRuI6a4DoCnsQzftv0GYAsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:31.649495Z"},"content_sha256":"5008e1007859950df40a2c4c63a432d69f91306841977843a1b107bebd57e6d7","schema_version":"1.0","event_id":"sha256:5008e1007859950df40a2c4c63a432d69f91306841977843a1b107bebd57e6d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NPXG26NONTZMMBTILRZ3EY6KWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Federated Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hankz Hankui Zhuo, Qiang Yang, Qian Xu, Wenfeng Feng, Yufeng Lin","submitted_at":"2019-01-24T08:25:29Z","abstract_excerpt":"In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Despite the success of previous transfer learning approaches in deep reinforcement learning, directly transferring data or models from an agent to another agent is often not allowed due to the privacy of data and/or models in many privacy-aware applications. In this paper, we propose a novel deep reinforcement learning framework to federatively build models of high-quality for agents with consideration of their privacies, namely Federated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08277","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/1901.08277/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":"2026-07-05T00:39:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D7A4JtDnh+T8qU99BF/CSCQUIXm2PwF5ArGsBC1zPh7J1kmRC9Qk0tKgh6diBRjMfa4HSyyUsP+oMutLUqVABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:39:31.650052Z"},"content_sha256":"eee5455923c7aac7f89448b8fe55e6cd1bb80cdc459a4a684b73a06bf0001106","schema_version":"1.0","event_id":"sha256:eee5455923c7aac7f89448b8fe55e6cd1bb80cdc459a4a684b73a06bf0001106"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/bundle.json","state_url":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPXG26NONTZMMBTILRZ3EY6KWU/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":"2026-08-07T17:39:31Z","links":{"resolver":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU","bundle":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/bundle.json","state":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPXG26NONTZMMBTILRZ3EY6KWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NPXG26NONTZMMBTILRZ3EY6KWU","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":"e9ad04da246cd2bd9ce8a12c7074f479d74e10440b951b03d1839a9029254f90","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","title_canon_sha256":"baa2ca1e5118de87056e5ffae21af3e7079a173583dbbc0356cd0f6c1f723730"},"schema_version":"1.0","source":{"id":"1901.08277","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08277","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08277v3","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08277","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"NPXG26NONTZM","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_16","alias_value":"NPXG26NONTZMMBTI","created_at":"2026-07-05T00:39:10Z"},{"alias_kind":"pith_short_8","alias_value":"NPXG26NO","created_at":"2026-07-05T00:39:10Z"}],"graph_snapshots":[{"event_id":"sha256:eee5455923c7aac7f89448b8fe55e6cd1bb80cdc459a4a684b73a06bf0001106","target":"graph","created_at":"2026-07-05T00:39:10Z","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/1901.08277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Despite the success of previous transfer learning approaches in deep reinforcement learning, directly transferring data or models from an agent to another agent is often not allowed due to the privacy of data and/or models in many privacy-aware applications. In this paper, we propose a novel deep reinforcement learning framework to federatively build models of high-quality for agents with consideration of their privacies, namely Federated ","authors_text":"Hankz Hankui Zhuo, Qiang Yang, Qian Xu, Wenfeng Feng, Yufeng Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","title":"Federated Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08277","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":"sha256:5008e1007859950df40a2c4c63a432d69f91306841977843a1b107bebd57e6d7","target":"record","created_at":"2026-07-05T00:39:10Z","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":"e9ad04da246cd2bd9ce8a12c7074f479d74e10440b951b03d1839a9029254f90","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","title_canon_sha256":"baa2ca1e5118de87056e5ffae21af3e7079a173583dbbc0356cd0f6c1f723730"},"schema_version":"1.0","source":{"id":"1901.08277","kind":"arxiv","version":3}},"canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","first_computed_at":"2026-07-05T00:39:10.069373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:39:10.069373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zX5wbMXsg/7dQ8G0Im2yKCfj7g9NWXHxVIStX9UG51DN8ybpV+Eytmy3FmaaDwxEIOXgNGpo41RJMpI40NOxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:39:10.069805Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08277","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5008e1007859950df40a2c4c63a432d69f91306841977843a1b107bebd57e6d7","sha256:eee5455923c7aac7f89448b8fe55e6cd1bb80cdc459a4a684b73a06bf0001106"],"state_sha256":"762f93ef313f28a640ace530f43dd22ae2a7bee9b77a4258c126e430c725f69a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FSSoAmCMi9WsbrDMHahEj/FFdKskOUUwt/x21df8EguXLdXGVzHtR15DP8e5ZcKYWjLcsZ9FOD1RCcTp+6KDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:39:31.654958Z","bundle_sha256":"6f7b63579e0da1feba9948df145edde216b85d4799c727b7a1bf89d4490fcf7b"}}