{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KRC6W63LKDCN3QUEMPVI567MVT","short_pith_number":"pith:KRC6W63L","schema_version":"1.0","canonical_sha256":"5445eb7b6b50c4ddc28463ea8efbecacfa92f3b5b3d23144ba0c5a1f5b492ac3","source":{"kind":"arxiv","id":"2412.18781","version":2},"attestation_state":"computed","paper":{"title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Hiroshi Kera, Kazuhiko Kawamoto, Shingo Ayabe, Takuto Otomo","submitted_at":"2024-12-25T05:02:22Z","abstract_excerpt":"Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinforcement learning, is particularly promising for robot control applications. Nevertheless, its robustness against real-world challenges, such as joint actuator faults in robots, remains a critical concern. This study evaluates the robustness of existing offline reinforcement learning methods using legged robots from OpenAI Gym based on average episodic rewards. For robustness evaluation, we simulate failures by incorpo"},"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":"2412.18781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-25T05:02:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de8e8d80d22c2f6e56e86432343b0774b2700e63ded88a099f6511ea33eca3c2","abstract_canon_sha256":"78eda16be8a27c37f709cf64800ba98318c5653ccad33f88cc60699d835c2323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:06.173060Z","signature_b64":"6bK05uNU1csMwOhKB/Bmr3XLWodn0SMFV/NZN5tdXacuSpw8YhZQATCDRiWnYWjQ3wupnUR7Rg7vNpVnNj3FCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5445eb7b6b50c4ddc28463ea8efbecacfa92f3b5b3d23144ba0c5a1f5b492ac3","last_reissued_at":"2026-07-05T11:39:06.172569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:06.172569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Hiroshi Kera, Kazuhiko Kawamoto, Shingo Ayabe, Takuto Otomo","submitted_at":"2024-12-25T05:02:22Z","abstract_excerpt":"Offline reinforcement learning, which learns solely from datasets without environmental interaction, has gained attention. This approach, similar to traditional online deep reinforcement learning, is particularly promising for robot control applications. Nevertheless, its robustness against real-world challenges, such as joint actuator faults in robots, remains a critical concern. This study evaluates the robustness of existing offline reinforcement learning methods using legged robots from OpenAI Gym based on average episodic rewards. For robustness evaluation, we simulate failures by incorpo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18781","kind":"arxiv","version":2},"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/2412.18781/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":"2412.18781","created_at":"2026-07-05T11:39:06.172625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18781v2","created_at":"2026-07-05T11:39:06.172625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18781","created_at":"2026-07-05T11:39:06.172625+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRC6W63LKDCN","created_at":"2026-07-05T11:39:06.172625+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRC6W63LKDCN3QUE","created_at":"2026-07-05T11:39:06.172625+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRC6W63L","created_at":"2026-07-05T11:39:06.172625+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/KRC6W63LKDCN3QUEMPVI567MVT","json":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT.json","graph_json":"https://pith.science/api/pith-number/KRC6W63LKDCN3QUEMPVI567MVT/graph.json","events_json":"https://pith.science/api/pith-number/KRC6W63LKDCN3QUEMPVI567MVT/events.json","paper":"https://pith.science/paper/KRC6W63L"},"agent_actions":{"view_html":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT","download_json":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT.json","view_paper":"https://pith.science/paper/KRC6W63L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18781&json=true","fetch_graph":"https://pith.science/api/pith-number/KRC6W63LKDCN3QUEMPVI567MVT/graph.json","fetch_events":"https://pith.science/api/pith-number/KRC6W63LKDCN3QUEMPVI567MVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT/action/storage_attestation","attest_author":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT/action/author_attestation","sign_citation":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT/action/citation_signature","submit_replication":"https://pith.science/pith/KRC6W63LKDCN3QUEMPVI567MVT/action/replication_record"}},"created_at":"2026-07-05T11:39:06.172625+00:00","updated_at":"2026-07-05T11:39:06.172625+00:00"}