{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R63XHGHAEXFSBEEYYG6QZKP7KL","short_pith_number":"pith:R63XHGHA","schema_version":"1.0","canonical_sha256":"8fb77398e025cb209098c1bd0ca9ff52e2124e9176a0ccd59c15abc4c72c97d0","source":{"kind":"arxiv","id":"2203.10033","version":1},"attestation_state":"computed","paper":{"title":"Skill-based Multi-objective Reinforcement Learning of Industrial Robot Tasks with Planning and Knowledge Integration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Faseeh Ahmad, Konstantinos Chatzilygeroudis, Luigi Nardi, Matthias Mayr, Volker Krueger","submitted_at":"2022-03-18T16:03:27Z","abstract_excerpt":"In modern industrial settings with small batch sizes it should be easy to set up a robot system for a new task. Strategies exist, e.g. the use of skills, but when it comes to handling forces and torques, these systems often fall short. We introduce an approach that provides a combination of task-level planning with targeted learning of scenario-specific parameters for skill-based systems. We propose the following pipeline: (1) the user provides a task goal in the planning language PDDL, (2) a plan (i.e., a sequence of skills) is generated and the learnable parameters of the skills are automati"},"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":"2203.10033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2022-03-18T16:03:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"80e3b863d6b1d20edcf0b2b4f7283e172ef552d8c2ad7462f25ae7a32dc8b93c","abstract_canon_sha256":"7154ecdbcb48ab1812730b359dc631bd6eeb495ee976efdc5185512c08193caa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:27.204947Z","signature_b64":"R7hxvwMT1y3dQU0GYEgISTgijp0IxHIsSlZrlIe7eLwQWsov8N/owuxpRG1QBs92aKZPY+Ou0cfcmCCM7uNMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb77398e025cb209098c1bd0ca9ff52e2124e9176a0ccd59c15abc4c72c97d0","last_reissued_at":"2026-07-05T04:06:27.204428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:27.204428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill-based Multi-objective Reinforcement Learning of Industrial Robot Tasks with Planning and Knowledge Integration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Faseeh Ahmad, Konstantinos Chatzilygeroudis, Luigi Nardi, Matthias Mayr, Volker Krueger","submitted_at":"2022-03-18T16:03:27Z","abstract_excerpt":"In modern industrial settings with small batch sizes it should be easy to set up a robot system for a new task. Strategies exist, e.g. the use of skills, but when it comes to handling forces and torques, these systems often fall short. We introduce an approach that provides a combination of task-level planning with targeted learning of scenario-specific parameters for skill-based systems. We propose the following pipeline: (1) the user provides a task goal in the planning language PDDL, (2) a plan (i.e., a sequence of skills) is generated and the learnable parameters of the skills are automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10033","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10033/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":"2203.10033","created_at":"2026-07-05T04:06:27.204490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10033v1","created_at":"2026-07-05T04:06:27.204490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10033","created_at":"2026-07-05T04:06:27.204490+00:00"},{"alias_kind":"pith_short_12","alias_value":"R63XHGHAEXFS","created_at":"2026-07-05T04:06:27.204490+00:00"},{"alias_kind":"pith_short_16","alias_value":"R63XHGHAEXFSBEEY","created_at":"2026-07-05T04:06:27.204490+00:00"},{"alias_kind":"pith_short_8","alias_value":"R63XHGHA","created_at":"2026-07-05T04:06:27.204490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.11468","citing_title":"Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09198","citing_title":"Understanding High-Dimensional Bayesian Optimization","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL","json":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL.json","graph_json":"https://pith.science/api/pith-number/R63XHGHAEXFSBEEYYG6QZKP7KL/graph.json","events_json":"https://pith.science/api/pith-number/R63XHGHAEXFSBEEYYG6QZKP7KL/events.json","paper":"https://pith.science/paper/R63XHGHA"},"agent_actions":{"view_html":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL","download_json":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL.json","view_paper":"https://pith.science/paper/R63XHGHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10033&json=true","fetch_graph":"https://pith.science/api/pith-number/R63XHGHAEXFSBEEYYG6QZKP7KL/graph.json","fetch_events":"https://pith.science/api/pith-number/R63XHGHAEXFSBEEYYG6QZKP7KL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL/action/storage_attestation","attest_author":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL/action/author_attestation","sign_citation":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL/action/citation_signature","submit_replication":"https://pith.science/pith/R63XHGHAEXFSBEEYYG6QZKP7KL/action/replication_record"}},"created_at":"2026-07-05T04:06:27.204490+00:00","updated_at":"2026-07-05T04:06:27.204490+00:00"}