{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SWG23O5X3HMI6KNBMX6K6RZ5UN","short_pith_number":"pith:SWG23O5X","canonical_record":{"source":{"id":"2110.07392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","cross_cats_sorted":["cs.MA","math.OC"],"title_canon_sha256":"1f1b9dde08f3ea8e09264fd609468c1b728692bbc705b7a99e82e9ebd6056cb9","abstract_canon_sha256":"9b74ec37688ba044b738f8eda4982636659c4446638459e299a757abd00dd026"},"schema_version":"1.0"},"canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","source":{"kind":"arxiv","id":"2110.07392","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07392","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07392v2","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07392","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"SWG23O5X3HMI","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"SWG23O5X3HMI6KNB","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"SWG23O5X","created_at":"2026-07-05T04:19:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SWG23O5X3HMI6KNBMX6K6RZ5UN","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","cross_cats_sorted":["cs.MA","math.OC"],"title_canon_sha256":"1f1b9dde08f3ea8e09264fd609468c1b728692bbc705b7a99e82e9ebd6056cb9","abstract_canon_sha256":"9b74ec37688ba044b738f8eda4982636659c4446638459e299a757abd00dd026"},"schema_version":"1.0"},"canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:22.598531Z","signature_b64":"aulzAds3chyoxKARzv2czjkyVI4Ql9pdm1O1xb7IjoCcj6K5tmL4GuKdInRBgLYb7xw5cLc4wNwGnCY0uHEmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","last_reissued_at":"2026-07-05T04:19:22.598065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:22.598065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07392","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:19:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KC2DeJRYS0t/sLDYfB1VDyUPjfL1+9HBeAL/OopTAnWggGnaT+qZ6sMglzY+OuJIX2USjeTewen1gEqlfcI3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:47:28.539423Z"},"content_sha256":"a284c44a047fae620a4a091bd21cde493a4f9123bff04afebeb924b4ed34c0c0","schema_version":"1.0","event_id":"sha256:a284c44a047fae620a4a091bd21cde493a4f9123bff04afebeb924b4ed34c0c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SWG23O5X3HMI6KNBMX6K6RZ5UN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Justin Lidard, Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2021-10-14T14:27:27Z","abstract_excerpt":"A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when exploration is fully decentralized. Specifically, we consider a class of online, episodic, tabular $Q$-learning problems under time-varying reward and transition dynamics, in which agents can communicate in a decentralized manner.We show that group performance, as measured by the bound on regret, can be significantly improved through communication when each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07392","kind":"arxiv","version":2},"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/2110.07392/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":"2026-07-05T04:19:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSjWO5A64eyXuJ9iBac+St6ba8Bd1r/JnH8A0f8de8vZe5VviXXY0Iyf9kDCopb/u/TfNQAiy4Gp4u7YYMbQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:47:28.539951Z"},"content_sha256":"b27720567f19b86e0eb9dc1d895f717cfa4c18c963c9b031eb428be70e1c52fb","schema_version":"1.0","event_id":"sha256:b27720567f19b86e0eb9dc1d895f717cfa4c18c963c9b031eb428be70e1c52fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/bundle.json","state_url":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/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":"2026-08-14T10:47:28Z","links":{"resolver":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN","bundle":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/bundle.json","state":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SWG23O5X3HMI6KNBMX6K6RZ5UN","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":"9b74ec37688ba044b738f8eda4982636659c4446638459e299a757abd00dd026","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","title_canon_sha256":"1f1b9dde08f3ea8e09264fd609468c1b728692bbc705b7a99e82e9ebd6056cb9"},"schema_version":"1.0","source":{"id":"2110.07392","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07392","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07392v2","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07392","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"SWG23O5X3HMI","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"SWG23O5X3HMI6KNB","created_at":"2026-07-05T04:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"SWG23O5X","created_at":"2026-07-05T04:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:b27720567f19b86e0eb9dc1d895f717cfa4c18c963c9b031eb428be70e1c52fb","target":"graph","created_at":"2026-07-05T04:19:22Z","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/2110.07392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when exploration is fully decentralized. Specifically, we consider a class of online, episodic, tabular $Q$-learning problems under time-varying reward and transition dynamics, in which agents can communicate in a decentralized manner.We show that group performance, as measured by the bound on regret, can be significantly improved through communication when each","authors_text":"Justin Lidard, Naomi Ehrich Leonard, Udari Madhushani","cross_cats":["cs.MA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07392","kind":"arxiv","version":2},"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:a284c44a047fae620a4a091bd21cde493a4f9123bff04afebeb924b4ed34c0c0","target":"record","created_at":"2026-07-05T04:19:22Z","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":"9b74ec37688ba044b738f8eda4982636659c4446638459e299a757abd00dd026","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","title_canon_sha256":"1f1b9dde08f3ea8e09264fd609468c1b728692bbc705b7a99e82e9ebd6056cb9"},"schema_version":"1.0","source":{"id":"2110.07392","kind":"arxiv","version":2}},"canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","first_computed_at":"2026-07-05T04:19:22.598065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:22.598065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aulzAds3chyoxKARzv2czjkyVI4Ql9pdm1O1xb7IjoCcj6K5tmL4GuKdInRBgLYb7xw5cLc4wNwGnCY0uHEmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:22.598531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07392","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a284c44a047fae620a4a091bd21cde493a4f9123bff04afebeb924b4ed34c0c0","sha256:b27720567f19b86e0eb9dc1d895f717cfa4c18c963c9b031eb428be70e1c52fb"],"state_sha256":"677405abe5280fa98a98e532bbfd1c23eb4f213e3800e3033c4ec5feda3593a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLUeMJ1+Fyz4Q1JWfhvqPcsUmo+afBBc4jcJiwRZOA19UqL9NBYJHEcmuDE6IKNp9udlXDep2JrhyuLCKDE1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:47:28.545137Z","bundle_sha256":"e0086893f5beeb8a1fb148e1bc42b50436b811efb4c6d636cba002e0a694eaf1"}}