{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SNDIY673M2UWFEJYIHC5RHVTZH","short_pith_number":"pith:SNDIY673","schema_version":"1.0","canonical_sha256":"93468c7bfb66a962913841c5d89eb3c9f7142563619da8f891ca43ff58ac9f3b","source":{"kind":"arxiv","id":"2305.00561","version":1},"attestation_state":"computed","paper":{"title":"Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Junchao Li, Mingyu Cai, Shaoping Xiao, Zhen Kan","submitted_at":"2023-04-30T19:57:39Z","abstract_excerpt":"Motion planning of autonomous agents in partially known environments with incomplete information is a challenging problem, particularly for complex tasks. This paper proposes a model-free reinforcement learning approach to address this problem. We formulate motion planning as a probabilistic-labeled partially observable Markov decision process (PL-POMDP) problem and use linear temporal logic (LTL) to express the complex task. The LTL formula is then converted to a limit-deterministic generalized B\\\"uchi automaton (LDGBA). The problem is redefined as finding an optimal policy on the product of "},"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":"2305.00561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-04-30T19:57:39Z","cross_cats_sorted":["cs.FL","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"315af225b418e7dc02c7481c3c2f6151572413f523a479dee4a183a1af10321f","abstract_canon_sha256":"c6674d9d2d29b3d4447d70d09e88ca7cb0523e0d347a1ac92fb3141fd56c15b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:42.845389Z","signature_b64":"PzKoi9hwN7qX2Bs4XGLlL4QaaCSALDhWt8zQ4vmP7CvuSPvTYqMwXXOHxjY3nHB4UYMMoHKaUOsXW9WrG6SAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93468c7bfb66a962913841c5d89eb3c9f7142563619da8f891ca43ff58ac9f3b","last_reissued_at":"2026-07-05T06:05:42.844999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:42.844999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Junchao Li, Mingyu Cai, Shaoping Xiao, Zhen Kan","submitted_at":"2023-04-30T19:57:39Z","abstract_excerpt":"Motion planning of autonomous agents in partially known environments with incomplete information is a challenging problem, particularly for complex tasks. This paper proposes a model-free reinforcement learning approach to address this problem. We formulate motion planning as a probabilistic-labeled partially observable Markov decision process (PL-POMDP) problem and use linear temporal logic (LTL) to express the complex task. The LTL formula is then converted to a limit-deterministic generalized B\\\"uchi automaton (LDGBA). The problem is redefined as finding an optimal policy on the product of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00561","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/2305.00561/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":"2305.00561","created_at":"2026-07-05T06:05:42.845056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00561v1","created_at":"2026-07-05T06:05:42.845056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00561","created_at":"2026-07-05T06:05:42.845056+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNDIY673M2UW","created_at":"2026-07-05T06:05:42.845056+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNDIY673M2UWFEJY","created_at":"2026-07-05T06:05:42.845056+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNDIY673","created_at":"2026-07-05T06:05:42.845056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10803","citing_title":"Developing and Integrating Trust Modeling into Multi-Objective Reinforcement Learning for Intelligent Agricultural Management","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH","json":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH.json","graph_json":"https://pith.science/api/pith-number/SNDIY673M2UWFEJYIHC5RHVTZH/graph.json","events_json":"https://pith.science/api/pith-number/SNDIY673M2UWFEJYIHC5RHVTZH/events.json","paper":"https://pith.science/paper/SNDIY673"},"agent_actions":{"view_html":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH","download_json":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH.json","view_paper":"https://pith.science/paper/SNDIY673","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00561&json=true","fetch_graph":"https://pith.science/api/pith-number/SNDIY673M2UWFEJYIHC5RHVTZH/graph.json","fetch_events":"https://pith.science/api/pith-number/SNDIY673M2UWFEJYIHC5RHVTZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH/action/storage_attestation","attest_author":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH/action/author_attestation","sign_citation":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH/action/citation_signature","submit_replication":"https://pith.science/pith/SNDIY673M2UWFEJYIHC5RHVTZH/action/replication_record"}},"created_at":"2026-07-05T06:05:42.845056+00:00","updated_at":"2026-07-05T06:05:42.845056+00:00"}