{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3IDVRV3UZ4RVEPTECQGULO3K3I","short_pith_number":"pith:3IDVRV3U","schema_version":"1.0","canonical_sha256":"da0758d774cf23523e64140d45bb6ada2beb8b33094db8f21bae274375ff1dcf","source":{"kind":"arxiv","id":"2007.15724","version":1},"attestation_state":"computed","paper":{"title":"MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Baiming Chen, Ding Zhao, Guru Koushik, Hongyi Zhou, Martial Hebert, Zuxin Liu","submitted_at":"2020-07-30T20:14:42Z","abstract_excerpt":"Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a glo"},"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":"2007.15724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-07-30T20:14:42Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"ab94577aa012767c094b8d5977017b55b5f4b37bf27a7232346e647c287233e8","abstract_canon_sha256":"06ea21af6f4afe926611c2380477c91d6abdeb5bf80291f29a71b98fb1c3d9bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:37.698063Z","signature_b64":"/t6MWRuO54DgPV1WtD855BBe5gVcfbp+sl0P5eaXieu5ULEONgd5aTkYaxasSxQ5FiMJ+vZ/wlk+TxHJhrqADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da0758d774cf23523e64140d45bb6ada2beb8b33094db8f21bae274375ff1dcf","last_reissued_at":"2026-07-05T01:23:37.697685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:37.697685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Baiming Chen, Ding Zhao, Guru Koushik, Hongyi Zhou, Martial Hebert, Zuxin Liu","submitted_at":"2020-07-30T20:14:42Z","abstract_excerpt":"Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a glo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15724","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/2007.15724/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":"2007.15724","created_at":"2026-07-05T01:23:37.697741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15724v1","created_at":"2026-07-05T01:23:37.697741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15724","created_at":"2026-07-05T01:23:37.697741+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IDVRV3UZ4RV","created_at":"2026-07-05T01:23:37.697741+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IDVRV3UZ4RVEPTE","created_at":"2026-07-05T01:23:37.697741+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IDVRV3U","created_at":"2026-07-05T01:23:37.697741+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/3IDVRV3UZ4RVEPTECQGULO3K3I","json":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I.json","graph_json":"https://pith.science/api/pith-number/3IDVRV3UZ4RVEPTECQGULO3K3I/graph.json","events_json":"https://pith.science/api/pith-number/3IDVRV3UZ4RVEPTECQGULO3K3I/events.json","paper":"https://pith.science/paper/3IDVRV3U"},"agent_actions":{"view_html":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I","download_json":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I.json","view_paper":"https://pith.science/paper/3IDVRV3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15724&json=true","fetch_graph":"https://pith.science/api/pith-number/3IDVRV3UZ4RVEPTECQGULO3K3I/graph.json","fetch_events":"https://pith.science/api/pith-number/3IDVRV3UZ4RVEPTECQGULO3K3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I/action/storage_attestation","attest_author":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I/action/author_attestation","sign_citation":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I/action/citation_signature","submit_replication":"https://pith.science/pith/3IDVRV3UZ4RVEPTECQGULO3K3I/action/replication_record"}},"created_at":"2026-07-05T01:23:37.697741+00:00","updated_at":"2026-07-05T01:23:37.697741+00:00"}