{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX","short_pith_number":"pith:PIQSC3RZ","schema_version":"1.0","canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","source":{"kind":"arxiv","id":"2410.06347","version":2},"attestation_state":"computed","paper":{"title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dominik \\.Zurek, Kamil Faber, Marcin Pietro\\'n, Pawe{\\l} Gajewski","submitted_at":"2024-10-08T20:35:30Z","abstract_excerpt":"Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While Offline RL mitigates the need for costly online interactions, its integration with goal-conditioned policies and transformer-based architectures remains underexplored. We introduce a Goal-Conditioned Decision Transformer adapted for offline multi-goal robotics. By explicitly incorporating goal states into the sequence modeling framework, our approach efficiently solves varying tasks using only pre-collected data. We validate this method on a newly release"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.06347","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T20:35:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8fe069eba42c134b57383c0da4518828a371a88f8c5e640b133ad5a7366ae57","abstract_canon_sha256":"357b46dd5d9fff5059260461cb086f17d457ee040860ae14470c708be443c5b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:20.697234Z","signature_b64":"OJzAGkNCcjq5XemQ+1kGJlpDbJJC9UZvnZGYgjucAPPtIryAVrkVf1SSr8ZbbRXshxeN52lVQsBH6NlBFUz4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","last_reissued_at":"2026-06-30T01:17:20.696364Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:20.696364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dominik \\.Zurek, Kamil Faber, Marcin Pietro\\'n, Pawe{\\l} Gajewski","submitted_at":"2024-10-08T20:35:30Z","abstract_excerpt":"Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While Offline RL mitigates the need for costly online interactions, its integration with goal-conditioned policies and transformer-based architectures remains underexplored. We introduce a Goal-Conditioned Decision Transformer adapted for offline multi-goal robotics. By explicitly incorporating goal states into the sequence modeling framework, our approach efficiently solves varying tasks using only pre-collected data. We validate this method on a newly release"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that our approach outperforms state-of-the-art online baselines in complex tasks and maintains robustness in sparse-reward settings, even with limited expert demonstrations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The newly released offline dataset for the Franka Emika Panda platform contains sufficient coverage of varying goals and task distributions to support generalization of the goal-conditioned policy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"46aee2f2464f78695ec23e481e1fa5db33cea3b711f125768d5b6025d0fd5653"},"source":{"id":"2410.06347","kind":"arxiv","version":2},"verdict":{"id":"763aed6a-5d64-4f01-af8a-e6561eaee0ca","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T19:17:55.724494Z","strongest_claim":"Experimental results demonstrate that our approach outperforms state-of-the-art online baselines in complex tasks and maintains robustness in sparse-reward settings, even with limited expert demonstrations.","one_line_summary":"A Goal-Conditioned Decision Transformer is adapted for offline multi-goal RL and shown to outperform online baselines on a new Franka Emika Panda dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The newly released offline dataset for the Franka Emika Panda platform contains sufficient coverage of varying goals and task distributions to support generalization of the goal-conditioned policy.","pith_extraction_headline":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.06347/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":47,"sample":[{"doi":"","year":2023,"title":"Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning","work_id":"3118549e-dd15-4a2b-b12a-24dea48f5f49","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Efficient reinforcement learning for autonomous driving with parameterized skills and priors","work_id":"1d307660-5b4d-4a1b-9a8b-d2cafc8ade99","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Accelerating reinforcement learning for autonomous driving using task-agnostic and ego-centric motion skills","work_id":"f96e0b91-27d5-4a91-87e5-7a028e7b697a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"A review paper on implementing reinforcement learning technique in optimising games performance","work_id":"1d3d4815-5b61-43f0-b520-a2861ad6e203","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Modeling decisions in games using reinforcement learning","work_id":"b17fd2f8-7b44-4acd-8f9d-0d3a31fbbc54","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":47,"snapshot_sha256":"7d94eb00448a5b2243b6055c3b3968c887f6570405f846d3497ceff8540aa7c5","internal_anchors":4},"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":"2410.06347","created_at":"2026-06-30T01:17:20.696478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06347v2","created_at":"2026-06-30T01:17:20.696478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06347","created_at":"2026-06-30T01:17:20.696478+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIQSC3RZPOCT","created_at":"2026-06-30T01:17:20.696478+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIQSC3RZPOCTKT4W","created_at":"2026-06-30T01:17:20.696478+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIQSC3RZ","created_at":"2026-06-30T01:17:20.696478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.20194","citing_title":"MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20194","citing_title":"MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31727","citing_title":"Focal Plate Prototyping for Modular Focal Planes of Stage-5 Instruments For Ground-Based Telescopes","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19211","citing_title":"Thermal Characterization of a 6-Positioner, 6.2-mm-Pitch Module for Stage-5 Telescopes","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20194","citing_title":"MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX","json":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX.json","graph_json":"https://pith.science/api/pith-number/PIQSC3RZPOCTKT4WBQXOQJENTX/graph.json","events_json":"https://pith.science/api/pith-number/PIQSC3RZPOCTKT4WBQXOQJENTX/events.json","paper":"https://pith.science/paper/PIQSC3RZ"},"agent_actions":{"view_html":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX","download_json":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX.json","view_paper":"https://pith.science/paper/PIQSC3RZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06347&json=true","fetch_graph":"https://pith.science/api/pith-number/PIQSC3RZPOCTKT4WBQXOQJENTX/graph.json","fetch_events":"https://pith.science/api/pith-number/PIQSC3RZPOCTKT4WBQXOQJENTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/action/storage_attestation","attest_author":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/action/author_attestation","sign_citation":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/action/citation_signature","submit_replication":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/action/replication_record"}},"created_at":"2026-06-30T01:17:20.696478+00:00","updated_at":"2026-06-30T01:17:20.696478+00:00"}