{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GLVLIHYKXPKC337HGWKYS763LL","short_pith_number":"pith:GLVLIHYK","schema_version":"1.0","canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","source":{"kind":"arxiv","id":"1804.10500","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Ali Ghadirzadeh, John Folkesson, Patric Jensfelt, Xi Chen","submitted_at":"2018-04-27T13:40:20Z","abstract_excerpt":"Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multif"},"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":"1804.10500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-27T13:40:20Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"423b7ec7f37f306e1c9b5495b4147fcb0aebb27efc6ee08e9dd35b46ce6c355f","abstract_canon_sha256":"315d6af469fc0577ef470fc614f82df6b06f5d737c1bac33941dda573a45e745"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:20.585507Z","signature_b64":"JfmEVPH/TPFUD4kKxBY1NIJHpclZRm0F2qvW9oVoYaoKhI/OJei62UpBdqfxRet3owObr4Q0tFD4/Z4XUEWbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","last_reissued_at":"2026-05-18T00:17:20.584741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:20.584741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Ali Ghadirzadeh, John Folkesson, Patric Jensfelt, Xi Chen","submitted_at":"2018-04-27T13:40:20Z","abstract_excerpt":"Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10500","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":""},"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":"1804.10500","created_at":"2026-05-18T00:17:20.584860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10500v1","created_at":"2026-05-18T00:17:20.584860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10500","created_at":"2026-05-18T00:17:20.584860+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLVLIHYKXPKC","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLVLIHYKXPKC337H","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLVLIHYK","created_at":"2026-05-18T12:32:25.280505+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/GLVLIHYKXPKC337HGWKYS763LL","json":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL.json","graph_json":"https://pith.science/api/pith-number/GLVLIHYKXPKC337HGWKYS763LL/graph.json","events_json":"https://pith.science/api/pith-number/GLVLIHYKXPKC337HGWKYS763LL/events.json","paper":"https://pith.science/paper/GLVLIHYK"},"agent_actions":{"view_html":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL","download_json":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL.json","view_paper":"https://pith.science/paper/GLVLIHYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10500&json=true","fetch_graph":"https://pith.science/api/pith-number/GLVLIHYKXPKC337HGWKYS763LL/graph.json","fetch_events":"https://pith.science/api/pith-number/GLVLIHYKXPKC337HGWKYS763LL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/action/storage_attestation","attest_author":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/action/author_attestation","sign_citation":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/action/citation_signature","submit_replication":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/action/replication_record"}},"created_at":"2026-05-18T00:17:20.584860+00:00","updated_at":"2026-05-18T00:17:20.584860+00:00"}