{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QH3BTW33I2MALTU4D3XW5E2MBX","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":"4c29970f5083c314e848f4975e342eb025057adbe42279abd0cabf7aa52c1b1e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T11:05:41Z","title_canon_sha256":"9a651c12ada03eae158b687d147384ce494a60314e739cf186b6fc665f4e14ce"},"schema_version":"1.0","source":{"id":"2003.11881","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.11881","created_at":"2026-07-05T02:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2003.11881v2","created_at":"2026-07-05T02:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11881","created_at":"2026-07-05T02:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"QH3BTW33I2MA","created_at":"2026-07-05T02:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"QH3BTW33I2MALTU4","created_at":"2026-07-05T02:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"QH3BTW33","created_at":"2026-07-05T02:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:a6bafd5b1cf9cc70afc770c03cb13b6b9885c8c849120025c900f3f6a8b28e57","target":"graph","created_at":"2026-07-05T02:20:13Z","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/2003.11881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. In this work, we identify and formalize a series of independent challenges that embody the difficulties that must be addressed for RL to be commonly deployed in real-world systems. For each challenge, we define it formally in the context of a Markov Decision Process, analyze the effects of th","authors_text":"Cosmin Paduraru, Daniel J. Mankowitz, Gabriel Dulac-Arnold, Jerry Li, Nir Levine, Sven Gowal, Todd Hester","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T11:05:41Z","title":"An empirical investigation of the challenges of real-world reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11881","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":"sha256:757996d569c96c7a23615a18301f908c02bccf7ae40a064f1afaadc154945cc4","target":"record","created_at":"2026-07-05T02:20:13Z","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":"4c29970f5083c314e848f4975e342eb025057adbe42279abd0cabf7aa52c1b1e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T11:05:41Z","title_canon_sha256":"9a651c12ada03eae158b687d147384ce494a60314e739cf186b6fc665f4e14ce"},"schema_version":"1.0","source":{"id":"2003.11881","kind":"arxiv","version":2}},"canonical_sha256":"81f619db7b469805ce9c1eef6e934c0dd60d6297373256a95b4991d9981f16a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81f619db7b469805ce9c1eef6e934c0dd60d6297373256a95b4991d9981f16a7","first_computed_at":"2026-07-05T02:20:13.388473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:13.388473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O8Mi7uMn6toQueJ29gicDXczZNjG0b3PFLWgOE/AN4GEb2YCDLgNo3X4bh58B0jNBN7xXj2LtMCArqkyC6B9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:13.388966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.11881","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:757996d569c96c7a23615a18301f908c02bccf7ae40a064f1afaadc154945cc4","sha256:a6bafd5b1cf9cc70afc770c03cb13b6b9885c8c849120025c900f3f6a8b28e57"],"state_sha256":"2be86e0e356e2631f7c16c45e642f8ca6a6b4c2347c9ec69a5203e5be160d562"}