{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TIWLMLHUAFIH5BFQTRQUACSPQW","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":"f50fbdd673378768bc18bc157f8cc6e1e12560efb4b3cf08520eb947ecc8f3df","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T20:48:19Z","title_canon_sha256":"1270e190cc3e0d15b393591e29e3d832b9fe6e8a4a7b06ea7953a36e912b16db"},"schema_version":"1.0","source":{"id":"2206.08442","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08442","created_at":"2026-07-05T08:54:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08442v3","created_at":"2026-07-05T08:54:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08442","created_at":"2026-07-05T08:54:00Z"},{"alias_kind":"pith_short_12","alias_value":"TIWLMLHUAFIH","created_at":"2026-07-05T08:54:00Z"},{"alias_kind":"pith_short_16","alias_value":"TIWLMLHUAFIH5BFQ","created_at":"2026-07-05T08:54:00Z"},{"alias_kind":"pith_short_8","alias_value":"TIWLMLHU","created_at":"2026-07-05T08:54:00Z"}],"graph_snapshots":[{"event_id":"sha256:76d728c9695bfe12fb96ca78eac9ab4620c918002ad03f93c923db4a14ba5637","target":"graph","created_at":"2026-07-05T08:54:00Z","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/2206.08442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In model-based reinforcement learning (RL), an agent can leverage a learned model to improve its way of behaving in different ways. Two of the prevalent ways to do this are through decision-time and background planning methods. In this study, we are interested in understanding how the value-based versions of these two planning methods will compare against each other across different settings. Towards this goal, we first consider the simplest instantiations of value-based decision-time and background planning methods and provide theoretical results on which one will perform better in the regula","authors_text":"Doina Precup, Safa Alver","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T20:48:19Z","title":"A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08442","kind":"arxiv","version":3},"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":"sha256:5ebb30daf3605c18ae466f3bed230c8d69c315bf40fcdbb6d18711ac7babb2ab","target":"record","created_at":"2026-07-05T08:54:00Z","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":"f50fbdd673378768bc18bc157f8cc6e1e12560efb4b3cf08520eb947ecc8f3df","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T20:48:19Z","title_canon_sha256":"1270e190cc3e0d15b393591e29e3d832b9fe6e8a4a7b06ea7953a36e912b16db"},"schema_version":"1.0","source":{"id":"2206.08442","kind":"arxiv","version":3}},"canonical_sha256":"9a2cb62cf401507e84b09c61400a4f859fa99a2b2b86927ed5419b719bc8c35d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a2cb62cf401507e84b09c61400a4f859fa99a2b2b86927ed5419b719bc8c35d","first_computed_at":"2026-07-05T08:54:00.189188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:00.189188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8eq5D0KaGeaqILHCQR76gpp1IPuMOi5WxayT2rhYpgXoidEnzKDrlUwr87qGuRYgkJm7A+W/M71oF8Ar9DzFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:00.189611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08442","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ebb30daf3605c18ae466f3bed230c8d69c315bf40fcdbb6d18711ac7babb2ab","sha256:76d728c9695bfe12fb96ca78eac9ab4620c918002ad03f93c923db4a14ba5637"],"state_sha256":"f3ac3e41efc13bdc9839f74f9c5721202cb1628751ff58c211a5668edddd62da"}