{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BAA3HTRBPDZITKHT4ILSKEU7SX","short_pith_number":"pith:BAA3HTRB","schema_version":"1.0","canonical_sha256":"0801b3ce2178f289a8f3e21725129f95c065700bdbbe20b030706a43aa96be65","source":{"kind":"arxiv","id":"2301.11721","version":2},"attestation_state":"computed","paper":{"title":"Single-Trajectory Distributionally Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiheng Zhang, Jose Blanchet, Xiaoteng Ma, Zhengyuan Zhou, Zhipeng Liang","submitted_at":"2023-01-27T14:08:09Z","abstract_excerpt":"To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As a price for robustness gain, DRRL involves optimizing over a set of distributions, which is inherently more challenging than optimizing over a fixed distribution in the non-robust case. Existing DRRL algorithms are either model-based or fail to learn from a single sample trajectory. In this paper, w"},"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":"2301.11721","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-27T14:08:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"005d0fe023f7cd315afbe9586cb40208b8e5760f335e08bc8b9e154bdfd983df","abstract_canon_sha256":"73afefa980662420aba2cab2733d7fe9677f08210c7a9a6ac6edb2a6ed321d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:50.470977Z","signature_b64":"ldUqXmX6gPAxraiuCWVC73kzVkVmXGFcKhmeqLC7nI40/kekYE8dfU8GmahO+znE9c3Uv+emvnSblCsXNgQcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0801b3ce2178f289a8f3e21725129f95c065700bdbbe20b030706a43aa96be65","last_reissued_at":"2026-07-05T09:09:50.470454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:50.470454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Trajectory Distributionally Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jiheng Zhang, Jose Blanchet, Xiaoteng Ma, Zhengyuan Zhou, Zhipeng Liang","submitted_at":"2023-01-27T14:08:09Z","abstract_excerpt":"To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As a price for robustness gain, DRRL involves optimizing over a set of distributions, which is inherently more challenging than optimizing over a fixed distribution in the non-robust case. Existing DRRL algorithms are either model-based or fail to learn from a single sample trajectory. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11721","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/2301.11721/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":"2301.11721","created_at":"2026-07-05T09:09:50.470523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11721v2","created_at":"2026-07-05T09:09:50.470523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11721","created_at":"2026-07-05T09:09:50.470523+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAA3HTRBPDZI","created_at":"2026-07-05T09:09:50.470523+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAA3HTRBPDZITKHT","created_at":"2026-07-05T09:09:50.470523+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAA3HTRB","created_at":"2026-07-05T09:09:50.470523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08417","citing_title":"Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX","json":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX.json","graph_json":"https://pith.science/api/pith-number/BAA3HTRBPDZITKHT4ILSKEU7SX/graph.json","events_json":"https://pith.science/api/pith-number/BAA3HTRBPDZITKHT4ILSKEU7SX/events.json","paper":"https://pith.science/paper/BAA3HTRB"},"agent_actions":{"view_html":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX","download_json":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX.json","view_paper":"https://pith.science/paper/BAA3HTRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11721&json=true","fetch_graph":"https://pith.science/api/pith-number/BAA3HTRBPDZITKHT4ILSKEU7SX/graph.json","fetch_events":"https://pith.science/api/pith-number/BAA3HTRBPDZITKHT4ILSKEU7SX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX/action/storage_attestation","attest_author":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX/action/author_attestation","sign_citation":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX/action/citation_signature","submit_replication":"https://pith.science/pith/BAA3HTRBPDZITKHT4ILSKEU7SX/action/replication_record"}},"created_at":"2026-07-05T09:09:50.470523+00:00","updated_at":"2026-07-05T09:09:50.470523+00:00"}