{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6DXSKQK6XQOGNVJ4BFBMRNED42","short_pith_number":"pith:6DXSKQK6","schema_version":"1.0","canonical_sha256":"f0ef25415ebc1c66d53c0942c8b483e6898b299ba45736d39dea146ac8bfaa87","source":{"kind":"arxiv","id":"2106.02039","version":4},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Michael Janner, Qiyang Li, Sergey Levine","submitted_at":"2021-06-03T17:58:51Z","abstract_excerpt":"Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem, with the goal being to produce a sequence of actions that leads to a sequence of high rewards. Viewed in this way, it is tempting to consider whether high-capacity sequence prediction models that work well in other domains, such as natural-language processing, can also provide effective solutions to the RL problem. To this end, we explore how RL can be tack"},"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":"2106.02039","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-03T17:58:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53ca4f9090f667e4148c5dd3f0af63d7fe42986d6f89aede11ac709f9a77fe6d","abstract_canon_sha256":"3cae8cb34516d0a53fae987b254858d875c1a03199c9afdf83e119eb5badc989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:29.160428Z","signature_b64":"GZz7LQPRTKRMp0yVM1/owFnuzoyrUZvQ6Vjq92U4XEA2y4mzcPNDvBQwtE4lut19qCySBRpwuNhF5gvvOQLMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ef25415ebc1c66d53c0942c8b483e6898b299ba45736d39dea146ac8bfaa87","last_reissued_at":"2026-07-05T03:35:29.160022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:29.160022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Michael Janner, Qiyang Li, Sergey Levine","submitted_at":"2021-06-03T17:58:51Z","abstract_excerpt":"Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem, with the goal being to produce a sequence of actions that leads to a sequence of high rewards. Viewed in this way, it is tempting to consider whether high-capacity sequence prediction models that work well in other domains, such as natural-language processing, can also provide effective solutions to the RL problem. To this end, we explore how RL can be tack"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02039","kind":"arxiv","version":4},"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/2106.02039/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":"2106.02039","created_at":"2026-07-05T03:35:29.160075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02039v4","created_at":"2026-07-05T03:35:29.160075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02039","created_at":"2026-07-05T03:35:29.160075+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DXSKQK6XQOG","created_at":"2026-07-05T03:35:29.160075+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DXSKQK6XQOGNVJ4","created_at":"2026-07-05T03:35:29.160075+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DXSKQK6","created_at":"2026-07-05T03:35:29.160075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27806","citing_title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19538","citing_title":"DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12116","citing_title":"Neural CDEs as Correctors for Learned Time Series Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08404","citing_title":"Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42","json":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42.json","graph_json":"https://pith.science/api/pith-number/6DXSKQK6XQOGNVJ4BFBMRNED42/graph.json","events_json":"https://pith.science/api/pith-number/6DXSKQK6XQOGNVJ4BFBMRNED42/events.json","paper":"https://pith.science/paper/6DXSKQK6"},"agent_actions":{"view_html":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42","download_json":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42.json","view_paper":"https://pith.science/paper/6DXSKQK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02039&json=true","fetch_graph":"https://pith.science/api/pith-number/6DXSKQK6XQOGNVJ4BFBMRNED42/graph.json","fetch_events":"https://pith.science/api/pith-number/6DXSKQK6XQOGNVJ4BFBMRNED42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42/action/storage_attestation","attest_author":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42/action/author_attestation","sign_citation":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42/action/citation_signature","submit_replication":"https://pith.science/pith/6DXSKQK6XQOGNVJ4BFBMRNED42/action/replication_record"}},"created_at":"2026-07-05T03:35:29.160075+00:00","updated_at":"2026-07-05T03:35:29.160075+00:00"}