{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NHL4W465CIG5EL3A2STVM5V5QF","short_pith_number":"pith:NHL4W465","schema_version":"1.0","canonical_sha256":"69d7cb73dd120dd22f60d4a75676bd8150ba7d823aa9c8cfde184c11cb81cb85","source":{"kind":"arxiv","id":"1911.04448","version":4},"attestation_state":"computed","paper":{"title":"Real-Time Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Pal, Simon Ramstedt","submitted_at":"2019-11-11T18:52:04Z","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"},"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":"1911.04448","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-11T18:52:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d4a5915b5a8dbe9dc9d460e66fe59ffa28af8976f30a13566b863067cab0ab3a","abstract_canon_sha256":"80817a71831fbb83c1f3226573a1243d5dd10b88cf7923e91c5b55423aeaa4c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:39.864108Z","signature_b64":"thEEO566bFEWw/b4UqBBXRWo/awVV0mqbk9W9nWLCkjv3pccHhxzYx3KndwB3kUGn1gj5e9bYgSZccfB00UxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69d7cb73dd120dd22f60d4a75676bd8150ba7d823aa9c8cfde184c11cb81cb85","last_reissued_at":"2026-07-05T00:25:39.863668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:39.863668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-Time Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Pal, Simon Ramstedt","submitted_at":"2019-11-11T18:52:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04448","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/1911.04448/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":"1911.04448","created_at":"2026-07-05T00:25:39.863724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.04448v4","created_at":"2026-07-05T00:25:39.863724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04448","created_at":"2026-07-05T00:25:39.863724+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHL4W465CIG5","created_at":"2026-07-05T00:25:39.863724+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHL4W465CIG5EL3A","created_at":"2026-07-05T00:25:39.863724+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHL4W465","created_at":"2026-07-05T00:25:39.863724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.15621","citing_title":"Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF","json":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF.json","graph_json":"https://pith.science/api/pith-number/NHL4W465CIG5EL3A2STVM5V5QF/graph.json","events_json":"https://pith.science/api/pith-number/NHL4W465CIG5EL3A2STVM5V5QF/events.json","paper":"https://pith.science/paper/NHL4W465"},"agent_actions":{"view_html":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF","download_json":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF.json","view_paper":"https://pith.science/paper/NHL4W465","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.04448&json=true","fetch_graph":"https://pith.science/api/pith-number/NHL4W465CIG5EL3A2STVM5V5QF/graph.json","fetch_events":"https://pith.science/api/pith-number/NHL4W465CIG5EL3A2STVM5V5QF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF/action/storage_attestation","attest_author":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF/action/author_attestation","sign_citation":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF/action/citation_signature","submit_replication":"https://pith.science/pith/NHL4W465CIG5EL3A2STVM5V5QF/action/replication_record"}},"created_at":"2026-07-05T00:25:39.863724+00:00","updated_at":"2026-07-05T00:25:39.863724+00:00"}