{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BAA3HTRBPDZITKHT4ILSKEU7SX","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":"73afefa980662420aba2cab2733d7fe9677f08210c7a9a6ac6edb2a6ed321d02","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-27T14:08:09Z","title_canon_sha256":"005d0fe023f7cd315afbe9586cb40208b8e5760f335e08bc8b9e154bdfd983df"},"schema_version":"1.0","source":{"id":"2301.11721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11721","created_at":"2026-07-05T09:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11721v2","created_at":"2026-07-05T09:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11721","created_at":"2026-07-05T09:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"BAA3HTRBPDZI","created_at":"2026-07-05T09:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"BAA3HTRBPDZITKHT","created_at":"2026-07-05T09:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"BAA3HTRB","created_at":"2026-07-05T09:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:ae46c299abb70353060d264017d71c3201621bc946eb1e2a57d0351e1ea6480c","target":"graph","created_at":"2026-07-05T09:09:50Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.11721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiheng Zhang, Jose Blanchet, Xiaoteng Ma, Zhengyuan Zhou, Zhipeng Liang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-27T14:08:09Z","title":"Single-Trajectory Distributionally Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11721","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9e14f88dc3ffcc4d33ba62eb6d813c75f67b40128ee857893c39679e3545de4b","target":"record","created_at":"2026-07-05T09:09:50Z","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":"73afefa980662420aba2cab2733d7fe9677f08210c7a9a6ac6edb2a6ed321d02","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-27T14:08:09Z","title_canon_sha256":"005d0fe023f7cd315afbe9586cb40208b8e5760f335e08bc8b9e154bdfd983df"},"schema_version":"1.0","source":{"id":"2301.11721","kind":"arxiv","version":2}},"canonical_sha256":"0801b3ce2178f289a8f3e21725129f95c065700bdbbe20b030706a43aa96be65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0801b3ce2178f289a8f3e21725129f95c065700bdbbe20b030706a43aa96be65","first_computed_at":"2026-07-05T09:09:50.470454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:50.470454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldUqXmX6gPAxraiuCWVC73kzVkVmXGFcKhmeqLC7nI40/kekYE8dfU8GmahO+znE9c3Uv+emvnSblCsXNgQcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:50.470977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e14f88dc3ffcc4d33ba62eb6d813c75f67b40128ee857893c39679e3545de4b","sha256:ae46c299abb70353060d264017d71c3201621bc946eb1e2a57d0351e1ea6480c"],"state_sha256":"41d0b2e2fcfeeff25249d91db1ed0c534c1575677a28aeb8fbc73b420e9667ad"}