{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VOQ2BR2A5QFVA5R3LIBU2A5H4H","short_pith_number":"pith:VOQ2BR2A","schema_version":"1.0","canonical_sha256":"aba1a0c740ec0b50763b5a034d03a7e1d444a1b5d39b7b4b081e1e6daae3cfd4","source":{"kind":"arxiv","id":"2003.04371","version":3},"attestation_state":"computed","paper":{"title":"A Multi-Agent Reinforcement Learning Approach For Safe and Efficient Behavior Planning Of Connected Autonomous Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Caiwen Ding, Fei Miao, Jiangwei Wang, Jie Fu, Lynn Pepin, Shanglin Zhou, Songyang Han","submitted_at":"2020-03-09T19:15:30Z","abstract_excerpt":"The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather information about their environment by vehicle-to-vehicle (V2V) communication. In this work, we design an information-sharing-based multi-agent reinforcement learning (MARL) framework for CAVs, to take advantage of the extra information when making decisions to improve traffic efficiency and safety. The safe actor-critic algorithm we propose has two new techniques: the truncated Q-function and safe action mapping. The truncated Q-function utilizes the shared information from neighboring CAVs su"},"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":"2003.04371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-09T19:15:30Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"77e9393cc78036aac9a437b25b85289b9c11d2ab894d2f3d826a6565e6480b23","abstract_canon_sha256":"c3cb03295315ce3fe8d1a9cc0a27ad614b2ea874049c2a955c71b2592f9668dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:11.640790Z","signature_b64":"wwmT9j6QpZ91dt1jVMW3OuEpgMf9V0kTdorUTrv/lQV6iAGRivF/hxUtXVGvsfRDbXq65A4EEW26DoTe+Xu/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba1a0c740ec0b50763b5a034d03a7e1d444a1b5d39b7b4b081e1e6daae3cfd4","last_reissued_at":"2026-07-05T04:54:11.640350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:11.640350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Agent Reinforcement Learning Approach For Safe and Efficient Behavior Planning Of Connected Autonomous Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Caiwen Ding, Fei Miao, Jiangwei Wang, Jie Fu, Lynn Pepin, Shanglin Zhou, Songyang Han","submitted_at":"2020-03-09T19:15:30Z","abstract_excerpt":"The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather information about their environment by vehicle-to-vehicle (V2V) communication. In this work, we design an information-sharing-based multi-agent reinforcement learning (MARL) framework for CAVs, to take advantage of the extra information when making decisions to improve traffic efficiency and safety. The safe actor-critic algorithm we propose has two new techniques: the truncated Q-function and safe action mapping. The truncated Q-function utilizes the shared information from neighboring CAVs su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04371","kind":"arxiv","version":3},"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/2003.04371/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":"2003.04371","created_at":"2026-07-05T04:54:11.640408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04371v3","created_at":"2026-07-05T04:54:11.640408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04371","created_at":"2026-07-05T04:54:11.640408+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOQ2BR2A5QFV","created_at":"2026-07-05T04:54:11.640408+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOQ2BR2A5QFVA5R3","created_at":"2026-07-05T04:54:11.640408+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOQ2BR2A","created_at":"2026-07-05T04:54:11.640408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14903","citing_title":"CoMoCAVs: Cohesive Decision-Guided Motion Planning for Connected and Autonomous Vehicles with Multi-Policy Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H","json":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H.json","graph_json":"https://pith.science/api/pith-number/VOQ2BR2A5QFVA5R3LIBU2A5H4H/graph.json","events_json":"https://pith.science/api/pith-number/VOQ2BR2A5QFVA5R3LIBU2A5H4H/events.json","paper":"https://pith.science/paper/VOQ2BR2A"},"agent_actions":{"view_html":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H","download_json":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H.json","view_paper":"https://pith.science/paper/VOQ2BR2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04371&json=true","fetch_graph":"https://pith.science/api/pith-number/VOQ2BR2A5QFVA5R3LIBU2A5H4H/graph.json","fetch_events":"https://pith.science/api/pith-number/VOQ2BR2A5QFVA5R3LIBU2A5H4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H/action/storage_attestation","attest_author":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H/action/author_attestation","sign_citation":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H/action/citation_signature","submit_replication":"https://pith.science/pith/VOQ2BR2A5QFVA5R3LIBU2A5H4H/action/replication_record"}},"created_at":"2026-07-05T04:54:11.640408+00:00","updated_at":"2026-07-05T04:54:11.640408+00:00"}