{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2O3OU3WJAW5AFCZCBP4JJSGRTW","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":"0fdd368e67682cb35d87e3ae71086bcff2b1922708188e7552a7874350d15550","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-14T17:36:33Z","title_canon_sha256":"5c6e962cd9b675539dd777bad884bcf8a21a7f8d10bf1d92ec4d450258aea10b"},"schema_version":"1.0","source":{"id":"1908.05256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05256","created_at":"2026-07-04T23:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05256v1","created_at":"2026-07-04T23:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05256","created_at":"2026-07-04T23:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"2O3OU3WJAW5A","created_at":"2026-07-04T23:56:37Z"},{"alias_kind":"pith_short_16","alias_value":"2O3OU3WJAW5AFCZC","created_at":"2026-07-04T23:56:37Z"},{"alias_kind":"pith_short_8","alias_value":"2O3OU3WJ","created_at":"2026-07-04T23:56:37Z"}],"graph_snapshots":[{"event_id":"sha256:441ec7c4b3b6be6727709efbe80c75d4472be7ab161b8e06d317b6834aa2a2c7","target":"graph","created_at":"2026-07-04T23:56:37Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.05256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training times are required and cannot be accelerated in contrast to simulated environments, and reward functions may be hard to specify/model and/or to compute. Moreover, the transfer of policies learned in a simulator to the real-world has limitations (reality gap). On the other hand, machine learning methods that rely on the transfer of human knowledge to an agent","authors_text":"Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober, Rodrigo P\\'erez-Dattari","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-14T17:36:33Z","title":"Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05256","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":"sha256:7bfb8de92e2a03c168f7021f7569b8d83d6aad5b655b232e1d3e0c7179338d23","target":"record","created_at":"2026-07-04T23:56:37Z","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":"0fdd368e67682cb35d87e3ae71086bcff2b1922708188e7552a7874350d15550","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-14T17:36:33Z","title_canon_sha256":"5c6e962cd9b675539dd777bad884bcf8a21a7f8d10bf1d92ec4d450258aea10b"},"schema_version":"1.0","source":{"id":"1908.05256","kind":"arxiv","version":1}},"canonical_sha256":"d3b6ea6ec905ba028b220bf894c8d19dab4beb075467e296108e020559be6a7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3b6ea6ec905ba028b220bf894c8d19dab4beb075467e296108e020559be6a7e","first_computed_at":"2026-07-04T23:56:37.950036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:56:37.950036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8kPngXE8tkRj0UGmGiXfZd5w31em4Ehr7UaA3JqOo3OSBIQv5YcKCHoS+spvVc+At3ddNqRWBUhnKCw1QjzkCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:56:37.950427Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bfb8de92e2a03c168f7021f7569b8d83d6aad5b655b232e1d3e0c7179338d23","sha256:441ec7c4b3b6be6727709efbe80c75d4472be7ab161b8e06d317b6834aa2a2c7"],"state_sha256":"0373371687cc15890bc00b97f6d0634a21a5024e15377b76e7b23a96a8a4ce6f"}