{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KPW6H4XHW764FRPNZFEC2JBK2Z","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":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4"},"schema_version":"1.0","source":{"id":"2011.06709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06709v2","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"KPW6H4XHW764","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"KPW6H4XHW764FRPN","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"KPW6H4XH","created_at":"2026-07-05T01:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793","target":"graph","created_at":"2026-07-05T01:54:32Z","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/2011.06709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem.","authors_text":"David Krueger, Jan Leike, John Salvatier, Owain Evans","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title":"Active Reinforcement Learning: Observing Rewards at a Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06709","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":"sha256:94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998","target":"record","created_at":"2026-07-05T01:54:32Z","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":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4"},"schema_version":"1.0","source":{"id":"2011.06709","kind":"arxiv","version":2}},"canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","first_computed_at":"2026-07-05T01:54:32.323124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:32.323124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UY95B370ncGIzdcnx92onPH0edrArOXSOiRUHl6vRtRGTkL5v26oNhi80MA3n/hRGqtHmgyTYm+uqtlC2RkMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:32.323582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998","sha256:262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793"],"state_sha256":"f2a9b8392c17956f6485fb147c31f9c778ec7cc5a5b23dd8d1efeca116159ae7"}