{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GLVLIHYKXPKC337HGWKYS763LL","short_pith_number":"pith:GLVLIHYK","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"},"canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","source":{"kind":"arxiv","id":"1804.10500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10500","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10500v1","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10500","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"GLVLIHYKXPKC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GLVLIHYKXPKC337H","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GLVLIHYK","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GLVLIHYKXPKC337HGWKYS763LL","target":"record","payload":{"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"},"canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","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"},"source_kind":"arxiv","source_id":"1804.10500","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdWTZPhHYplxlj4k95wrEajMYrXZjUmTwk+O7/h7uQd/spCS3WmP4NPsMRR7H86bKrYwDytJd2dPvnvDUSsZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:56:05.032088Z"},"content_sha256":"54d8a857e21f3337c698650ebc4f2265875bb7c6212e462587aa8d566f8a781f","schema_version":"1.0","event_id":"sha256:54d8a857e21f3337c698650ebc4f2265875bb7c6212e462587aa8d566f8a781f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GLVLIHYKXPKC337HGWKYS763LL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9AVwCCYic6Z24UgwzmBpHijYPOBQ+ObJOA5Pr0HE1NN0ELNHnmScSt7c7HOzgkj/2+D/bJF44mYXNsdOFOR4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:56:05.032465Z"},"content_sha256":"dde94fee5212b095f85df40f05ca57c3f768bc65e3a263aff921cff2e4832d66","schema_version":"1.0","event_id":"sha256:dde94fee5212b095f85df40f05ca57c3f768bc65e3a263aff921cff2e4832d66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/bundle.json","state_url":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLVLIHYKXPKC337HGWKYS763LL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T01:56:05Z","links":{"resolver":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL","bundle":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/bundle.json","state":"https://pith.science/pith/GLVLIHYKXPKC337HGWKYS763LL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLVLIHYKXPKC337HGWKYS763LL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GLVLIHYKXPKC337HGWKYS763LL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"315d6af469fc0577ef470fc614f82df6b06f5d737c1bac33941dda573a45e745","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-27T13:40:20Z","title_canon_sha256":"423b7ec7f37f306e1c9b5495b4147fcb0aebb27efc6ee08e9dd35b46ce6c355f"},"schema_version":"1.0","source":{"id":"1804.10500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10500","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10500v1","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10500","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"GLVLIHYKXPKC","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GLVLIHYKXPKC337H","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GLVLIHYK","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:dde94fee5212b095f85df40f05ca57c3f768bc65e3a263aff921cff2e4832d66","target":"graph","created_at":"2026-05-18T00:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ali Ghadirzadeh, John Folkesson, Patric Jensfelt, Xi Chen","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-27T13:40:20Z","title":"Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10500","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:54d8a857e21f3337c698650ebc4f2265875bb7c6212e462587aa8d566f8a781f","target":"record","created_at":"2026-05-18T00:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"315d6af469fc0577ef470fc614f82df6b06f5d737c1bac33941dda573a45e745","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-04-27T13:40:20Z","title_canon_sha256":"423b7ec7f37f306e1c9b5495b4147fcb0aebb27efc6ee08e9dd35b46ce6c355f"},"schema_version":"1.0","source":{"id":"1804.10500","kind":"arxiv","version":1}},"canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32eab41f0abbd42defe73595897fdb5aee42d8d82ead290902dd449c03eb25a7","first_computed_at":"2026-05-18T00:17:20.584741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:20.584741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JfmEVPH/TPFUD4kKxBY1NIJHpclZRm0F2qvW9oVoYaoKhI/OJei62UpBdqfxRet3owObr4Q0tFD4/Z4XUEWbAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:20.585507Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54d8a857e21f3337c698650ebc4f2265875bb7c6212e462587aa8d566f8a781f","sha256:dde94fee5212b095f85df40f05ca57c3f768bc65e3a263aff921cff2e4832d66"],"state_sha256":"41104c3b856df70685d76d1a1b6a2f9ea0dff2fce8a7113c24903bfb347e63ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMfhSLcYIkZJ6Gjr6WIkGvWClLMKLpp2KNvZPYJGSBqz0ZtXtHW1AXZrnJIpkOPflCpK/Ye3Iopx/i6UCEeiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:56:05.034486Z","bundle_sha256":"e05325391d2381d9d06a0060f19168493e6caa44af0a55d28637fcbdaa9fc2aa"}}