{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5DCCUNCNE5LSLMRCB45PDN7RB5","short_pith_number":"pith:5DCCUNCN","schema_version":"1.0","canonical_sha256":"e8c42a344d275725b2220f3af1b7f10f5d0b505e92c1e5aeb461dcfbe6860eb8","source":{"kind":"arxiv","id":"2004.02780","version":2},"attestation_state":"computed","paper":{"title":"Networked Multi-Agent Reinforcement Learning with Emergent Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Ambedkar Dukkipati, Rishi Hazra, Shubham Gupta","submitted_at":"2020-04-06T16:13:23Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to communicate with each other. Can the agents develop a language while learning to perform a common task? In this paper, we formulate and study a MARL problem where cooperative agents are connected to each other via a fixed underlying network. These agents can communicate along the edges of this network by exchanging discrete symbols. However, the semantics of these"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.02780","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-04-06T16:13:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30811f361eb76c09c438cb4541d58c03aa25ae0ee23ef9610d8aa86e1809fb6b","abstract_canon_sha256":"a64807c8fe8b0976a322cf4a10c1763ba4d76e185b961c4a511e2b53def26adb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:05.188730Z","signature_b64":"guOSLmGFikBbj6a0/Z/I3oJvMhHYg9wpKQupOo2qAQX3Sy0Yqo9eV8C9I3P9fADymV4ucyq6QxY2otzAhJ2JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8c42a344d275725b2220f3af1b7f10f5d0b505e92c1e5aeb461dcfbe6860eb8","last_reissued_at":"2026-07-05T00:54:05.188236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:05.188236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Networked Multi-Agent Reinforcement Learning with Emergent Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Ambedkar Dukkipati, Rishi Hazra, Shubham Gupta","submitted_at":"2020-04-06T16:13:23Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to communicate with each other. Can the agents develop a language while learning to perform a common task? In this paper, we formulate and study a MARL problem where cooperative agents are connected to each other via a fixed underlying network. These agents can communicate along the edges of this network by exchanging discrete symbols. However, the semantics of these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02780","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/2004.02780/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.02780","created_at":"2026-07-05T00:54:05.188295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02780v2","created_at":"2026-07-05T00:54:05.188295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02780","created_at":"2026-07-05T00:54:05.188295+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DCCUNCNE5LS","created_at":"2026-07-05T00:54:05.188295+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DCCUNCNE5LSLMRC","created_at":"2026-07-05T00:54:05.188295+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DCCUNCN","created_at":"2026-07-05T00:54:05.188295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09495","citing_title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5","json":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5.json","graph_json":"https://pith.science/api/pith-number/5DCCUNCNE5LSLMRCB45PDN7RB5/graph.json","events_json":"https://pith.science/api/pith-number/5DCCUNCNE5LSLMRCB45PDN7RB5/events.json","paper":"https://pith.science/paper/5DCCUNCN"},"agent_actions":{"view_html":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5","download_json":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5.json","view_paper":"https://pith.science/paper/5DCCUNCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02780&json=true","fetch_graph":"https://pith.science/api/pith-number/5DCCUNCNE5LSLMRCB45PDN7RB5/graph.json","fetch_events":"https://pith.science/api/pith-number/5DCCUNCNE5LSLMRCB45PDN7RB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5/action/storage_attestation","attest_author":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5/action/author_attestation","sign_citation":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5/action/citation_signature","submit_replication":"https://pith.science/pith/5DCCUNCNE5LSLMRCB45PDN7RB5/action/replication_record"}},"created_at":"2026-07-05T00:54:05.188295+00:00","updated_at":"2026-07-05T00:54:05.188295+00:00"}