{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NHL4W465CIG5EL3A2STVM5V5QF","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":"80817a71831fbb83c1f3226573a1243d5dd10b88cf7923e91c5b55423aeaa4c3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-11T18:52:04Z","title_canon_sha256":"d4a5915b5a8dbe9dc9d460e66fe59ffa28af8976f30a13566b863067cab0ab3a"},"schema_version":"1.0","source":{"id":"1911.04448","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04448","created_at":"2026-07-05T00:25:39Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04448v4","created_at":"2026-07-05T00:25:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04448","created_at":"2026-07-05T00:25:39Z"},{"alias_kind":"pith_short_12","alias_value":"NHL4W465CIG5","created_at":"2026-07-05T00:25:39Z"},{"alias_kind":"pith_short_16","alias_value":"NHL4W465CIG5EL3A","created_at":"2026-07-05T00:25:39Z"},{"alias_kind":"pith_short_8","alias_value":"NHL4W465","created_at":"2026-07-05T00:25:39Z"}],"graph_snapshots":[{"event_id":"sha256:4d93d2356349dc72b45f2362e7158e2f59939cf38bb4292b3cdd5f42bb572b3c","target":"graph","created_at":"2026-07-05T00:25:39Z","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/1911.04448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action selection. As RL systems based on MDPs begin to find application in real-world safety critical situations, this mismatch between the assumptions underlying classical MDPs and the reality of real-time computation may lead to undesirable outcomes. In this paper, we introduce a new framework, in which states and actions evolve simultaneously and show how it is r","authors_text":"Christopher Pal, Simon Ramstedt","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-11T18:52:04Z","title":"Real-Time Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04448","kind":"arxiv","version":4},"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":"sha256:030ba14318a4ce5481388aefe53f41bff7fd6d0c9153e84d60d6d25263aa788b","target":"record","created_at":"2026-07-05T00:25:39Z","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":"80817a71831fbb83c1f3226573a1243d5dd10b88cf7923e91c5b55423aeaa4c3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-11T18:52:04Z","title_canon_sha256":"d4a5915b5a8dbe9dc9d460e66fe59ffa28af8976f30a13566b863067cab0ab3a"},"schema_version":"1.0","source":{"id":"1911.04448","kind":"arxiv","version":4}},"canonical_sha256":"69d7cb73dd120dd22f60d4a75676bd8150ba7d823aa9c8cfde184c11cb81cb85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69d7cb73dd120dd22f60d4a75676bd8150ba7d823aa9c8cfde184c11cb81cb85","first_computed_at":"2026-07-05T00:25:39.863668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:39.863668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"thEEO566bFEWw/b4UqBBXRWo/awVV0mqbk9W9nWLCkjv3pccHhxzYx3KndwB3kUGn1gj5e9bYgSZccfB00UxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:39.864108Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.04448","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:030ba14318a4ce5481388aefe53f41bff7fd6d0c9153e84d60d6d25263aa788b","sha256:4d93d2356349dc72b45f2362e7158e2f59939cf38bb4292b3cdd5f42bb572b3c"],"state_sha256":"d92b8bee8e1c330d099fc4c470fa39d5545bcce09f51bd5d0ef953460be1e64d"}