{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TA2VHL6PTN546QS2G77M7BAGXN","short_pith_number":"pith:TA2VHL6P","schema_version":"1.0","canonical_sha256":"983553afcf9b7bcf425a37fecf8406bb6745bf1f53d567cefd787cd01718ad94","source":{"kind":"arxiv","id":"2412.20075","version":1},"attestation_state":"computed","paper":{"title":"Investigating the Impact of Communication-Induced Action Space on Exploration of Unknown Environments with Decentralized Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christoforos Kanellakis (1), Gabriele Calzolari (1), George Nikolakopoulos (1) ((1) Lule{\\aa} University of Technology), Vidya Sumathy (1)","submitted_at":"2024-12-28T08:02:45Z","abstract_excerpt":"This paper introduces a novel enhancement to the Decentralized Multi-Agent Reinforcement Learning (D-MARL) exploration by proposing communication-induced action space to improve the mapping efficiency of unknown environments using homogeneous agents. Efficient exploration of large environments relies heavily on inter-agent communication as real-world scenarios are often constrained by data transmission limits, such as signal latency and bandwidth. Our proposed method optimizes each agent's policy using the heterogeneous-agent proximal policy optimization algorithm, allowing agents to autonomou"},"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":"2412.20075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-28T08:02:45Z","cross_cats_sorted":[],"title_canon_sha256":"8cb902e1ac411b09be5e455057e8bb7b3f076066d3a9474bcf7c2c213362d241","abstract_canon_sha256":"55493d22764d8187b330b118daea48741a551c36811c0d91be40449e4fdb737f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:54.279261Z","signature_b64":"mZZowpPQjCtcWN6dg/LxwzluopWP7d0ZmfZBFtalVrcHUpeX5jPhsoO1U7P94tsKgArAN8yE/3zA3sMgG34XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"983553afcf9b7bcf425a37fecf8406bb6745bf1f53d567cefd787cd01718ad94","last_reissued_at":"2026-07-05T09:54:54.278755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:54.278755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating the Impact of Communication-Induced Action Space on Exploration of Unknown Environments with Decentralized Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christoforos Kanellakis (1), Gabriele Calzolari (1), George Nikolakopoulos (1) ((1) Lule{\\aa} University of Technology), Vidya Sumathy (1)","submitted_at":"2024-12-28T08:02:45Z","abstract_excerpt":"This paper introduces a novel enhancement to the Decentralized Multi-Agent Reinforcement Learning (D-MARL) exploration by proposing communication-induced action space to improve the mapping efficiency of unknown environments using homogeneous agents. Efficient exploration of large environments relies heavily on inter-agent communication as real-world scenarios are often constrained by data transmission limits, such as signal latency and bandwidth. Our proposed method optimizes each agent's policy using the heterogeneous-agent proximal policy optimization algorithm, allowing agents to autonomou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20075","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/2412.20075/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":"2412.20075","created_at":"2026-07-05T09:54:54.278821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20075v1","created_at":"2026-07-05T09:54:54.278821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20075","created_at":"2026-07-05T09:54:54.278821+00:00"},{"alias_kind":"pith_short_12","alias_value":"TA2VHL6PTN54","created_at":"2026-07-05T09:54:54.278821+00:00"},{"alias_kind":"pith_short_16","alias_value":"TA2VHL6PTN546QS2","created_at":"2026-07-05T09:54:54.278821+00:00"},{"alias_kind":"pith_short_8","alias_value":"TA2VHL6P","created_at":"2026-07-05T09:54:54.278821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN","json":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN.json","graph_json":"https://pith.science/api/pith-number/TA2VHL6PTN546QS2G77M7BAGXN/graph.json","events_json":"https://pith.science/api/pith-number/TA2VHL6PTN546QS2G77M7BAGXN/events.json","paper":"https://pith.science/paper/TA2VHL6P"},"agent_actions":{"view_html":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN","download_json":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN.json","view_paper":"https://pith.science/paper/TA2VHL6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20075&json=true","fetch_graph":"https://pith.science/api/pith-number/TA2VHL6PTN546QS2G77M7BAGXN/graph.json","fetch_events":"https://pith.science/api/pith-number/TA2VHL6PTN546QS2G77M7BAGXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN/action/storage_attestation","attest_author":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN/action/author_attestation","sign_citation":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN/action/citation_signature","submit_replication":"https://pith.science/pith/TA2VHL6PTN546QS2G77M7BAGXN/action/replication_record"}},"created_at":"2026-07-05T09:54:54.278821+00:00","updated_at":"2026-07-05T09:54:54.278821+00:00"}