{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KDESWZNMA2NVBDBFMYL3JGNMH2","short_pith_number":"pith:KDESWZNM","canonical_record":{"source":{"id":"2204.02634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T07:21:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a7be828eaaae1efdbb2b244184cc2fd9ac25d6f68e1f2a69dedc9336e2e92c03","abstract_canon_sha256":"0a254ebfb170b37fe807645c7eb2c72e51d83493729589a9453da9d0591e7d1e"},"schema_version":"1.0"},"canonical_sha256":"50c92b65ac069b508c256617b499ac3eba9bf1ff56d28d4544aae1441b7affe9","source":{"kind":"arxiv","id":"2204.02634","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02634","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02634v1","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02634","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"KDESWZNMA2NV","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"KDESWZNMA2NVBDBF","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"KDESWZNM","created_at":"2026-07-05T04:12:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KDESWZNMA2NVBDBFMYL3JGNMH2","target":"record","payload":{"canonical_record":{"source":{"id":"2204.02634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T07:21:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a7be828eaaae1efdbb2b244184cc2fd9ac25d6f68e1f2a69dedc9336e2e92c03","abstract_canon_sha256":"0a254ebfb170b37fe807645c7eb2c72e51d83493729589a9453da9d0591e7d1e"},"schema_version":"1.0"},"canonical_sha256":"50c92b65ac069b508c256617b499ac3eba9bf1ff56d28d4544aae1441b7affe9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:10.981499Z","signature_b64":"S4tCNPgG1dr0yCy2b3uhmFQX3ippAWggay5xKwKabYw/AGa+iRdymHSGnWm5LPY9r0BjS9jw9v0PysGs32ZRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c92b65ac069b508c256617b499ac3eba9bf1ff56d28d4544aae1441b7affe9","last_reissued_at":"2026-07-05T04:12:10.981061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:10.981061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.02634","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EzYoY/RD/6JYnC5raGmxLhz3IFMEnYok0UrLGsXmq/swrm0piw+NpEjjDFolJUljH70VsLm/1/1aQaqtD+dCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:49:46.514055Z"},"content_sha256":"6685c61a2341677fd7434af0103d75e717f99866ad92d14569a0a832d461ab57","schema_version":"1.0","event_id":"sha256:6685c61a2341677fd7434af0103d75e717f99866ad92d14569a0a832d461ab57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KDESWZNMA2NVBDBFMYL3JGNMH2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Federated Reinforcement Learning with Environment Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Jin, Shusen Wang, Wenhao Yang, Yang Peng, Zhihua Zhang","submitted_at":"2022-04-06T07:21:00Z","abstract_excerpt":"We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of environment heterogeneity, which means $n$ environments corresponding to these $n$ agents have different state transitions. To obtain a value function or a policy function which optimizes the overall performance in all environments, we propose two federated RL algorithms, \\texttt{QAvg} and \\texttt{PAvg}. We theoretically prove that these algorithms converge to subop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02634","kind":"arxiv","version":1},"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/2204.02634/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":"2026-07-05T04:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCZgp26LVF0dNeuLuNM4SpnibxDbLszEDpUdgsuBmYNwxgZlEjdXQJQ6GtNHPPqaeIRu7BWRTwNrb/HPTpVbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:49:46.514624Z"},"content_sha256":"0f000184d19f5bb2aa6b57dd9e19f834ded7b3ff1e23274b5be27a9459ea1780","schema_version":"1.0","event_id":"sha256:0f000184d19f5bb2aa6b57dd9e19f834ded7b3ff1e23274b5be27a9459ea1780"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/bundle.json","state_url":"https://pith.science/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/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":"2026-08-17T23:49:46Z","links":{"resolver":"https://pith.science/pith/KDESWZNMA2NVBDBFMYL3JGNMH2","bundle":"https://pith.science/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/bundle.json","state":"https://pith.science/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDESWZNMA2NVBDBFMYL3JGNMH2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KDESWZNMA2NVBDBFMYL3JGNMH2","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":"0a254ebfb170b37fe807645c7eb2c72e51d83493729589a9453da9d0591e7d1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T07:21:00Z","title_canon_sha256":"a7be828eaaae1efdbb2b244184cc2fd9ac25d6f68e1f2a69dedc9336e2e92c03"},"schema_version":"1.0","source":{"id":"2204.02634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02634","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02634v1","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02634","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"KDESWZNMA2NV","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"KDESWZNMA2NVBDBF","created_at":"2026-07-05T04:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"KDESWZNM","created_at":"2026-07-05T04:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:0f000184d19f5bb2aa6b57dd9e19f834ded7b3ff1e23274b5be27a9459ea1780","target":"graph","created_at":"2026-07-05T04:12:10Z","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/2204.02634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of environment heterogeneity, which means $n$ environments corresponding to these $n$ agents have different state transitions. To obtain a value function or a policy function which optimizes the overall performance in all environments, we propose two federated RL algorithms, \\texttt{QAvg} and \\texttt{PAvg}. We theoretically prove that these algorithms converge to subop","authors_text":"Hao Jin, Shusen Wang, Wenhao Yang, Yang Peng, Zhihua Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T07:21:00Z","title":"Federated Reinforcement Learning with Environment Heterogeneity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02634","kind":"arxiv","version":1},"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":"sha256:6685c61a2341677fd7434af0103d75e717f99866ad92d14569a0a832d461ab57","target":"record","created_at":"2026-07-05T04:12:10Z","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":"0a254ebfb170b37fe807645c7eb2c72e51d83493729589a9453da9d0591e7d1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T07:21:00Z","title_canon_sha256":"a7be828eaaae1efdbb2b244184cc2fd9ac25d6f68e1f2a69dedc9336e2e92c03"},"schema_version":"1.0","source":{"id":"2204.02634","kind":"arxiv","version":1}},"canonical_sha256":"50c92b65ac069b508c256617b499ac3eba9bf1ff56d28d4544aae1441b7affe9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50c92b65ac069b508c256617b499ac3eba9bf1ff56d28d4544aae1441b7affe9","first_computed_at":"2026-07-05T04:12:10.981061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:10.981061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S4tCNPgG1dr0yCy2b3uhmFQX3ippAWggay5xKwKabYw/AGa+iRdymHSGnWm5LPY9r0BjS9jw9v0PysGs32ZRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:10.981499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6685c61a2341677fd7434af0103d75e717f99866ad92d14569a0a832d461ab57","sha256:0f000184d19f5bb2aa6b57dd9e19f834ded7b3ff1e23274b5be27a9459ea1780"],"state_sha256":"64420d4503ff501b02b52134953427f5ded35047e43bf9d4a42fcbf59e0af1c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WORavrBmPCupIjqkcp16PvHOX1UWTlr5wTWDdnW+erJH7vJletPCU9qddurkHXDO3L7KSRYGAWbr4LzzkF5WDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:49:46.519935Z","bundle_sha256":"b0a9db0ea155eec3df77aef4a63f2d9c21226c8580de9fec59d358340e9b92da"}}