{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5DXFY5THZ5ZL2R4K4NS3RZBCAQ","short_pith_number":"pith:5DXFY5TH","schema_version":"1.0","canonical_sha256":"e8ee5c7667cf72bd478ae365b8e422040ac8132985c984e47989abc16a81e481","source":{"kind":"arxiv","id":"2202.13221","version":1},"attestation_state":"computed","paper":{"title":"RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Nikolaos Kourtzanidis, Sajad Saeedi","submitted_at":"2022-02-26T20:10:14Z","abstract_excerpt":"The objective of pose SLAM or pose-graph optimization (PGO) is to estimate the trajectory of a robot given odometric and loop closing constraints. State-of-the-art iterative approaches typically involve the linearization of a non-convex objective function and then repeatedly solve a set of normal equations. Furthermore, these methods may converge to a local minima yielding sub-optimal results. In this work, we present to the best of our knowledge the first Deep Reinforcement Learning (DRL) based environment and proposed agent for 2D pose-graph optimization. We demonstrate that the pose-graph o"},"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":"2202.13221","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-02-26T20:10:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b95ec9f33d4250d7b05026d26757960bf90c795f325a6610aa9ebaf446a1619","abstract_canon_sha256":"3518127f7c8a8d58291644590af0652ddf23af4c6c669a52d0d44c81042edc28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:27.193827Z","signature_b64":"mqzvwjmhC2PGhTNbYASTDaQLCyM+su9y2530shwuHueFqy7fhVgR3CW51bt2Bnyzmi4MvAdC4OOVTNYwXFGRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ee5c7667cf72bd478ae365b8e422040ac8132985c984e47989abc16a81e481","last_reissued_at":"2026-07-05T04:00:27.193405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:27.193405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Nikolaos Kourtzanidis, Sajad Saeedi","submitted_at":"2022-02-26T20:10:14Z","abstract_excerpt":"The objective of pose SLAM or pose-graph optimization (PGO) is to estimate the trajectory of a robot given odometric and loop closing constraints. State-of-the-art iterative approaches typically involve the linearization of a non-convex objective function and then repeatedly solve a set of normal equations. Furthermore, these methods may converge to a local minima yielding sub-optimal results. In this work, we present to the best of our knowledge the first Deep Reinforcement Learning (DRL) based environment and proposed agent for 2D pose-graph optimization. We demonstrate that the pose-graph o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13221","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/2202.13221/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":"2202.13221","created_at":"2026-07-05T04:00:27.193467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13221v1","created_at":"2026-07-05T04:00:27.193467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13221","created_at":"2026-07-05T04:00:27.193467+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DXFY5THZ5ZL","created_at":"2026-07-05T04:00:27.193467+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DXFY5THZ5ZL2R4K","created_at":"2026-07-05T04:00:27.193467+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DXFY5TH","created_at":"2026-07-05T04:00:27.193467+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/5DXFY5THZ5ZL2R4K4NS3RZBCAQ","json":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ.json","graph_json":"https://pith.science/api/pith-number/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/graph.json","events_json":"https://pith.science/api/pith-number/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/events.json","paper":"https://pith.science/paper/5DXFY5TH"},"agent_actions":{"view_html":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ","download_json":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ.json","view_paper":"https://pith.science/paper/5DXFY5TH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13221&json=true","fetch_graph":"https://pith.science/api/pith-number/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/action/storage_attestation","attest_author":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/action/author_attestation","sign_citation":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/action/citation_signature","submit_replication":"https://pith.science/pith/5DXFY5THZ5ZL2R4K4NS3RZBCAQ/action/replication_record"}},"created_at":"2026-07-05T04:00:27.193467+00:00","updated_at":"2026-07-05T04:00:27.193467+00:00"}