{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX","short_pith_number":"pith:PIQSC3RZ","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"},"canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","source":{"kind":"arxiv","id":"2410.06347","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06347","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06347v2","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06347","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"PIQSC3RZPOCT","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"PIQSC3RZPOCTKT4W","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"PIQSC3RZ","created_at":"2026-06-30T01:17:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX","target":"record","payload":{"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"},"canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","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"},"source_kind":"arxiv","source_id":"2410.06347","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1Vj4AWXNcMusQqklmEbJrGu9UqpKi1GYQBt2RnWih+/ZTGwe8lOiQG9PFRYJDaOU2UMa6suH1BRVXLoibmFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:15:55.668577Z"},"content_sha256":"bbcedcf46a8366c6fe31516763439d6681cc3750d51317ec28dd8802c4fcf447","schema_version":"1.0","event_id":"sha256:bbcedcf46a8366c6fe31516763439d6681cc3750d51317ec28dd8802c4fcf447"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX","target":"graph","payload":{"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"},"verdict_id":"763aed6a-5d64-4f01-af8a-e6561eaee0ca"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77x6WonyAn+kp35ub35rikGTZ6E73Kzb/DJ0AtuagiQzNv1V7ElFMaRWotax9HqqGhz5Ev8V9FpSSkVWBvtrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:15:55.669132Z"},"content_sha256":"bbfdd9f3c6c6d7a52dadbe17d6cf3f2c4d913d01892511ad45837242876e9166","schema_version":"1.0","event_id":"sha256:bbfdd9f3c6c6d7a52dadbe17d6cf3f2c4d913d01892511ad45837242876e9166"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/bundle.json","state_url":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T00:15:55Z","links":{"resolver":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX","bundle":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/bundle.json","state":"https://pith.science/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PIQSC3RZPOCTKT4WBQXOQJENTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PIQSC3RZPOCTKT4WBQXOQJENTX","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":"357b46dd5d9fff5059260461cb086f17d457ee040860ae14470c708be443c5b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T20:35:30Z","title_canon_sha256":"c8fe069eba42c134b57383c0da4518828a371a88f8c5e640b133ad5a7366ae57"},"schema_version":"1.0","source":{"id":"2410.06347","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06347","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06347v2","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06347","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"PIQSC3RZPOCT","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"PIQSC3RZPOCTKT4W","created_at":"2026-06-30T01:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"PIQSC3RZ","created_at":"2026-06-30T01:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:bbfdd9f3c6c6d7a52dadbe17d6cf3f2c4d913d01892511ad45837242876e9166","target":"graph","created_at":"2026-06-30T01:17:20Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone."}],"snapshot_sha256":"46aee2f2464f78695ec23e481e1fa5db33cea3b711f125768d5b6025d0fd5653"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.06347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dominik \\.Zurek, Kamil Faber, Marcin Pietro\\'n, Pawe{\\l} Gajewski","cross_cats":["cs.AI"],"headline":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T20:35:30Z","title":"Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning"},"references":{"count":47,"internal_anchors":4,"resolved_work":47,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning","work_id":"3118549e-dd15-4a2b-b12a-24dea48f5f49","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Efficient reinforcement learning for autonomous driving with parameterized skills and priors","work_id":"1d307660-5b4d-4a1b-9a8b-d2cafc8ade99","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Accelerating reinforcement learning for autonomous driving using task-agnostic and ego-centric motion skills","work_id":"f96e0b91-27d5-4a91-87e5-7a028e7b697a","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A review paper on implementing reinforcement learning technique in optimising games performance","work_id":"1d3d4815-5b61-43f0-b520-a2861ad6e203","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Modeling decisions in games using reinforcement learning","work_id":"b17fd2f8-7b44-4acd-8f9d-0d3a31fbbc54","year":2017}],"snapshot_sha256":"7d94eb00448a5b2243b6055c3b3968c887f6570405f846d3497ceff8540aa7c5"},"source":{"id":"2410.06347","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-23T19:17:55.724494Z","id":"763aed6a-5d64-4f01-af8a-e6561eaee0ca","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A goal-conditioned Decision Transformer learns multi-goal robotics policies from offline data alone.","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.","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."}},"verdict_id":"763aed6a-5d64-4f01-af8a-e6561eaee0ca"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bbcedcf46a8366c6fe31516763439d6681cc3750d51317ec28dd8802c4fcf447","target":"record","created_at":"2026-06-30T01:17:20Z","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":"357b46dd5d9fff5059260461cb086f17d457ee040860ae14470c708be443c5b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T20:35:30Z","title_canon_sha256":"c8fe069eba42c134b57383c0da4518828a371a88f8c5e640b133ad5a7366ae57"},"schema_version":"1.0","source":{"id":"2410.06347","kind":"arxiv","version":2}},"canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a21216e397b85354f960c2ee8248d9dc4e02c44b63e02d7c6337e0449ac020e","first_computed_at":"2026-06-30T01:17:20.696364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:20.696364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJzAGkNCcjq5XemQ+1kGJlpDbJJC9UZvnZGYgjucAPPtIryAVrkVf1SSr8ZbbRXshxeN52lVQsBH6NlBFUz4Aw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:20.697234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06347","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbcedcf46a8366c6fe31516763439d6681cc3750d51317ec28dd8802c4fcf447","sha256:bbfdd9f3c6c6d7a52dadbe17d6cf3f2c4d913d01892511ad45837242876e9166"],"state_sha256":"b2798ea7eac39ce53a8c02dfe79a9abeb8fc76f66d03f75bde05783503e7687c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8YBVBxYJm5VUB3svsCLyFNPqnXA0RPnvIQIEsKLXym9ssgnpD6nyalMg6rgcW20CVigR4yekGfgoyvu61oUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T00:15:55.671636Z","bundle_sha256":"47dec6372342ab91a9d990e71ea8b191d6cdaf4d95226178b10da950611b813c"}}