{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Q7L5FFPVL2WMFHEGGPNS3D4PSJ","short_pith_number":"pith:Q7L5FFPV","canonical_record":{"source":{"id":"2004.08883","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-19T15:42:55Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"508449cfee040e925bfbdcac62adb4640b6ab71fa1b914943fd6137098316bc0","abstract_canon_sha256":"dd464784a343794c6be208c6436848cde56565418ad5addff34fc1a09649489a"},"schema_version":"1.0"},"canonical_sha256":"87d7d295f55eacc29c8633db2d8f8f925455f15f328963a837e77272b86d6cc7","source":{"kind":"arxiv","id":"2004.08883","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08883","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08883v4","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08883","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"Q7L5FFPVL2WM","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"Q7L5FFPVL2WMFHEG","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"Q7L5FFPV","created_at":"2026-07-05T03:52:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Q7L5FFPVL2WMFHEGGPNS3D4PSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2004.08883","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-19T15:42:55Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"508449cfee040e925bfbdcac62adb4640b6ab71fa1b914943fd6137098316bc0","abstract_canon_sha256":"dd464784a343794c6be208c6436848cde56565418ad5addff34fc1a09649489a"},"schema_version":"1.0"},"canonical_sha256":"87d7d295f55eacc29c8633db2d8f8f925455f15f328963a837e77272b86d6cc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:23.857762Z","signature_b64":"iNpbib/zsBYQgk8tkXzBWrFY2zd1gTCSzwFTfr7S4HSWl78wkGwkkHDDI/5sP0WwKk4pFjz/KLzn96SLK3shAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d7d295f55eacc29c8633db2d8f8f925455f15f328963a837e77272b86d6cc7","last_reissued_at":"2026-07-05T03:52:23.857305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:23.857305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.08883","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":"2026-07-05T03:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7s6Grt0C1VZeVQcfVUUl1acBaaUxZZfZvVDR8GA021c08DBZtBj1HuBmGTvo0fDQfBiho7b0ZGClPwE9tjRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:37:45.853828Z"},"content_sha256":"a1c2fde5399e1f2010fe70992720900246c4178a138ab3b76501edddcebe7a25","schema_version":"1.0","event_id":"sha256:a1c2fde5399e1f2010fe70992720900246c4178a138ab3b76501edddcebe7a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Q7L5FFPVL2WMFHEGGPNS3D4PSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Policy Propagation for Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chang Liu, Chao Qu, Hui Li, James Zhang, Junwu Xiong, Le Song, Wei Chu, Weiqiang Wang, Yuan Qi","submitted_at":"2020-04-19T15:42:55Z","abstract_excerpt":"We propose a \\emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \\emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such that the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable. We evaluate our algorithm on several large scale challenging tasks and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08883","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.08883/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":"2026-07-05T03:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oD3vHATesvh3wt9zRN1chxjFPDANmwOlTikgKNjugSSdm2zj0VcBCOBCXuTgVLg4jHRPa9b/45ul9ss42A50AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:37:45.854218Z"},"content_sha256":"a2930abbdb750fe5e43f6d463f1eb4635283027d0fd42e05cf80be5b85dede31","schema_version":"1.0","event_id":"sha256:a2930abbdb750fe5e43f6d463f1eb4635283027d0fd42e05cf80be5b85dede31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/bundle.json","state_url":"https://pith.science/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/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":"2026-07-16T15:37:45Z","links":{"resolver":"https://pith.science/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ","bundle":"https://pith.science/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/bundle.json","state":"https://pith.science/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7L5FFPVL2WMFHEGGPNS3D4PSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q7L5FFPVL2WMFHEGGPNS3D4PSJ","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":"dd464784a343794c6be208c6436848cde56565418ad5addff34fc1a09649489a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-19T15:42:55Z","title_canon_sha256":"508449cfee040e925bfbdcac62adb4640b6ab71fa1b914943fd6137098316bc0"},"schema_version":"1.0","source":{"id":"2004.08883","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.08883","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2004.08883v4","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08883","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"Q7L5FFPVL2WM","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"Q7L5FFPVL2WMFHEG","created_at":"2026-07-05T03:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"Q7L5FFPV","created_at":"2026-07-05T03:52:23Z"}],"graph_snapshots":[{"event_id":"sha256:a2930abbdb750fe5e43f6d463f1eb4635283027d0fd42e05cf80be5b85dede31","target":"graph","created_at":"2026-07-05T03:52:23Z","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/2004.08883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a \\emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \\emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such that the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable. We evaluate our algorithm on several large scale challenging tasks and ","authors_text":"Chang Liu, Chao Qu, Hui Li, James Zhang, Junwu Xiong, Le Song, Wei Chu, Weiqiang Wang, Yuan Qi","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-19T15:42:55Z","title":"Variational Policy Propagation for Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08883","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:a1c2fde5399e1f2010fe70992720900246c4178a138ab3b76501edddcebe7a25","target":"record","created_at":"2026-07-05T03:52:23Z","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":"dd464784a343794c6be208c6436848cde56565418ad5addff34fc1a09649489a","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-19T15:42:55Z","title_canon_sha256":"508449cfee040e925bfbdcac62adb4640b6ab71fa1b914943fd6137098316bc0"},"schema_version":"1.0","source":{"id":"2004.08883","kind":"arxiv","version":4}},"canonical_sha256":"87d7d295f55eacc29c8633db2d8f8f925455f15f328963a837e77272b86d6cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87d7d295f55eacc29c8633db2d8f8f925455f15f328963a837e77272b86d6cc7","first_computed_at":"2026-07-05T03:52:23.857305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:52:23.857305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNpbib/zsBYQgk8tkXzBWrFY2zd1gTCSzwFTfr7S4HSWl78wkGwkkHDDI/5sP0WwKk4pFjz/KLzn96SLK3shAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:52:23.857762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.08883","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1c2fde5399e1f2010fe70992720900246c4178a138ab3b76501edddcebe7a25","sha256:a2930abbdb750fe5e43f6d463f1eb4635283027d0fd42e05cf80be5b85dede31"],"state_sha256":"04fa44baff2854f352bd983db6e41f1dec140fa513da72d3d2b80b73ada4883e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fspO+SgkugFA6EK265DEWMVy1BpbIjTQzHqIF1OihytHC0qqUT60g4ZIV2o9nib0WkrE/a7wPQyhAmG9Be51Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T15:37:45.856399Z","bundle_sha256":"7c42b775ce878152298d658bafe5de6131f1236ba1fce28b96bc08f3897704bb"}}