{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EQMG6AGBF7YQ6YY73B62KU33HE","short_pith_number":"pith:EQMG6AGB","canonical_record":{"source":{"id":"1711.08224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-11-22T10:54:09Z","cross_cats_sorted":[],"title_canon_sha256":"9d003f0206cea5270afeb490ace6be7ec9759c8d65304187b0934a7d92d96e6c","abstract_canon_sha256":"6d983d6bdb8b6cf8768bf39fcef632e50926f321a07be94ad42f9bcb31a41190"},"schema_version":"1.0"},"canonical_sha256":"24186f00c12ff10f631fd87da5537b3937ad9765172c5a5a602435385477b526","source":{"kind":"arxiv","id":"1711.08224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08224","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08224v1","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08224","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"EQMG6AGBF7YQ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EQMG6AGBF7YQ6YY7","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EQMG6AGB","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EQMG6AGBF7YQ6YY73B62KU33HE","target":"record","payload":{"canonical_record":{"source":{"id":"1711.08224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-11-22T10:54:09Z","cross_cats_sorted":[],"title_canon_sha256":"9d003f0206cea5270afeb490ace6be7ec9759c8d65304187b0934a7d92d96e6c","abstract_canon_sha256":"6d983d6bdb8b6cf8768bf39fcef632e50926f321a07be94ad42f9bcb31a41190"},"schema_version":"1.0"},"canonical_sha256":"24186f00c12ff10f631fd87da5537b3937ad9765172c5a5a602435385477b526","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:50.370722Z","signature_b64":"zQypV/5kZKLQP8AsaFXU9SqaMN/yu4B9p7wcnQxs694cnjjPy5+PbNLowgquY33iCxnnu0ghGrmgZv/Y9ULSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24186f00c12ff10f631fd87da5537b3937ad9765172c5a5a602435385477b526","last_reissued_at":"2026-05-18T00:29:50.370184Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:50.370184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.08224","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":"2026-05-18T00:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OkEdURM0412k3BFp/08aUhkDLhu/+6ka7SP8trjh0EpD5eKo3fjhGEEokdXvuTzRfLnw7gA14dBMFZr9yakrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:45:40.804226Z"},"content_sha256":"25813b178009c6404199ee18667b6c66e3a9152faa7d34b03d7f22f362396b94","schema_version":"1.0","event_id":"sha256:25813b178009c6404199ee18667b6c66e3a9152faa7d34b03d7f22f362396b94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EQMG6AGBF7YQ6YY73B62KU33HE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Depth Control of Model-Free AUVs via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cheng Wu, Hui Wu, Keyou You, Shiji Song","submitted_at":"2017-11-22T10:54:09Z","abstract_excerpt":"In this paper, we consider depth control problems of an autonomous underwater vehicle (AUV) for tracking the desired depth trajectories. Due to the unknown dynamical model of the AUV, the problems cannot be solved by most of model-based controllers. To this purpose, we formulate the depth control problems of the AUV as continuous-state, continuous-action Markov decision processes (MDPs) under unknown transition probabilities. Based on deterministic policy gradient (DPG) and neural network approximation, we propose a model-free reinforcement learning (RL) algorithm that learns a state-feedback "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08224","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":"2026-05-18T00:29:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+np8SAtJ7Q3zO+gHM18nchqJ9znXYhuCav7D66zjrNWE08MSBn+Chmq5VFMvBuj6+U8PV1H74TnQiSMFQh4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:45:40.804582Z"},"content_sha256":"e8aa9b0a0d8b0d140daa399884e7f144d80c99259a840f12e1087d0486a98d2d","schema_version":"1.0","event_id":"sha256:e8aa9b0a0d8b0d140daa399884e7f144d80c99259a840f12e1087d0486a98d2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQMG6AGBF7YQ6YY73B62KU33HE/bundle.json","state_url":"https://pith.science/pith/EQMG6AGBF7YQ6YY73B62KU33HE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQMG6AGBF7YQ6YY73B62KU33HE/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":"2026-07-01T07:45:40Z","links":{"resolver":"https://pith.science/pith/EQMG6AGBF7YQ6YY73B62KU33HE","bundle":"https://pith.science/pith/EQMG6AGBF7YQ6YY73B62KU33HE/bundle.json","state":"https://pith.science/pith/EQMG6AGBF7YQ6YY73B62KU33HE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQMG6AGBF7YQ6YY73B62KU33HE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EQMG6AGBF7YQ6YY73B62KU33HE","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":"6d983d6bdb8b6cf8768bf39fcef632e50926f321a07be94ad42f9bcb31a41190","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-11-22T10:54:09Z","title_canon_sha256":"9d003f0206cea5270afeb490ace6be7ec9759c8d65304187b0934a7d92d96e6c"},"schema_version":"1.0","source":{"id":"1711.08224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08224","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08224v1","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08224","created_at":"2026-05-18T00:29:50Z"},{"alias_kind":"pith_short_12","alias_value":"EQMG6AGBF7YQ","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EQMG6AGBF7YQ6YY7","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EQMG6AGB","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:e8aa9b0a0d8b0d140daa399884e7f144d80c99259a840f12e1087d0486a98d2d","target":"graph","created_at":"2026-05-18T00:29:50Z","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":"In this paper, we consider depth control problems of an autonomous underwater vehicle (AUV) for tracking the desired depth trajectories. Due to the unknown dynamical model of the AUV, the problems cannot be solved by most of model-based controllers. To this purpose, we formulate the depth control problems of the AUV as continuous-state, continuous-action Markov decision processes (MDPs) under unknown transition probabilities. Based on deterministic policy gradient (DPG) and neural network approximation, we propose a model-free reinforcement learning (RL) algorithm that learns a state-feedback ","authors_text":"Cheng Wu, Hui Wu, Keyou You, Shiji Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-11-22T10:54:09Z","title":"Depth Control of Model-Free AUVs via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08224","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":"sha256:25813b178009c6404199ee18667b6c66e3a9152faa7d34b03d7f22f362396b94","target":"record","created_at":"2026-05-18T00:29:50Z","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":"6d983d6bdb8b6cf8768bf39fcef632e50926f321a07be94ad42f9bcb31a41190","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-11-22T10:54:09Z","title_canon_sha256":"9d003f0206cea5270afeb490ace6be7ec9759c8d65304187b0934a7d92d96e6c"},"schema_version":"1.0","source":{"id":"1711.08224","kind":"arxiv","version":1}},"canonical_sha256":"24186f00c12ff10f631fd87da5537b3937ad9765172c5a5a602435385477b526","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24186f00c12ff10f631fd87da5537b3937ad9765172c5a5a602435385477b526","first_computed_at":"2026-05-18T00:29:50.370184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:50.370184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQypV/5kZKLQP8AsaFXU9SqaMN/yu4B9p7wcnQxs694cnjjPy5+PbNLowgquY33iCxnnu0ghGrmgZv/Y9ULSDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:50.370722Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25813b178009c6404199ee18667b6c66e3a9152faa7d34b03d7f22f362396b94","sha256:e8aa9b0a0d8b0d140daa399884e7f144d80c99259a840f12e1087d0486a98d2d"],"state_sha256":"6c6183c2c16a368eed6803e1f436572f4cf5cba70010ba4c566d05392bcb4b07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3fC4x+Yh2MTX+1EuwgnLVU6zkQVDmd+8GdVx0idY8aRq4+Nsf5+/02m1u/17ashwc+QAArbUSao7xDjNYeIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T07:45:40.806487Z","bundle_sha256":"9fbad9e9f7c21d4691b4252bec31ec6294a66a3d37c9212c8db97060b5faf3c1"}}