{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KAI5MWPDRXPYJALMRO3UQJBCZA","short_pith_number":"pith:KAI5MWPD","schema_version":"1.0","canonical_sha256":"5011d659e38ddf84816c8bb7482422c83aed921be1f41aab670f202a1da92684","source":{"kind":"arxiv","id":"2410.18519","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Controllers for Soft Robots using Learned Environments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jakob Foerster, Matthew Jackson, Niccol\\`o Enrico Veronese, Perla Maiolino, Uljad Berdica","submitted_at":"2024-10-24T08:11:34Z","abstract_excerpt":"Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptions, while learning-based techniques can be computationally demanding and limit the control policies to existing data. This paper introduces a novel approach to soft robotic control, leveraging state-of-the-art policy gradient methods within parallelizable synthetic environments learned from data. We also propose a safety oriented actuation space ex"},"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":"2410.18519","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-24T08:11:34Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"4f48ef640e681998dbdd2a91b6100d579d7532b435020b3d247c8ecc44063076","abstract_canon_sha256":"1041661ef24d0c62aab5f8fff21f639933bf4b4a1d25519e09f7f161afef07ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:49.172450Z","signature_b64":"tF6kYxFCPFjZ0o+BoeX4fPl4roz7bkI+Ab9g1z5a8XqmfRx8e/kIsXm+Zo47DhJoN5hhpDxAzEC8Er3JjQ6dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5011d659e38ddf84816c8bb7482422c83aed921be1f41aab670f202a1da92684","last_reissued_at":"2026-07-05T09:25:49.172066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:49.172066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Controllers for Soft Robots using Learned Environments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jakob Foerster, Matthew Jackson, Niccol\\`o Enrico Veronese, Perla Maiolino, Uljad Berdica","submitted_at":"2024-10-24T08:11:34Z","abstract_excerpt":"Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying assumptions, while learning-based techniques can be computationally demanding and limit the control policies to existing data. This paper introduces a novel approach to soft robotic control, leveraging state-of-the-art policy gradient methods within parallelizable synthetic environments learned from data. We also propose a safety oriented actuation space ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18519","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/2410.18519/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":"2410.18519","created_at":"2026-07-05T09:25:49.172114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18519v2","created_at":"2026-07-05T09:25:49.172114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18519","created_at":"2026-07-05T09:25:49.172114+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAI5MWPDRXPY","created_at":"2026-07-05T09:25:49.172114+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAI5MWPDRXPYJALM","created_at":"2026-07-05T09:25:49.172114+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAI5MWPD","created_at":"2026-07-05T09:25:49.172114+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/KAI5MWPDRXPYJALMRO3UQJBCZA","json":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA.json","graph_json":"https://pith.science/api/pith-number/KAI5MWPDRXPYJALMRO3UQJBCZA/graph.json","events_json":"https://pith.science/api/pith-number/KAI5MWPDRXPYJALMRO3UQJBCZA/events.json","paper":"https://pith.science/paper/KAI5MWPD"},"agent_actions":{"view_html":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA","download_json":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA.json","view_paper":"https://pith.science/paper/KAI5MWPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18519&json=true","fetch_graph":"https://pith.science/api/pith-number/KAI5MWPDRXPYJALMRO3UQJBCZA/graph.json","fetch_events":"https://pith.science/api/pith-number/KAI5MWPDRXPYJALMRO3UQJBCZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA/action/storage_attestation","attest_author":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA/action/author_attestation","sign_citation":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA/action/citation_signature","submit_replication":"https://pith.science/pith/KAI5MWPDRXPYJALMRO3UQJBCZA/action/replication_record"}},"created_at":"2026-07-05T09:25:49.172114+00:00","updated_at":"2026-07-05T09:25:49.172114+00:00"}