{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3XUZ4T7MLD4M4GBKM5VTK4FNM7","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":"46bd74bb16c349ebf171c6313764d1d9abe471601d455b63dfd64d4eb1876eb6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T22:39:57Z","title_canon_sha256":"99269deb6abfe8ed9eaa45d8e4e5a88893cc995919a669044fc6e33c56fb7633"},"schema_version":"1.0","source":{"id":"1905.13341","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13341","created_at":"2026-07-05T01:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13341v3","created_at":"2026-07-05T01:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13341","created_at":"2026-07-05T01:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"3XUZ4T7MLD4M","created_at":"2026-07-05T01:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"3XUZ4T7MLD4M4GBK","created_at":"2026-07-05T01:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"3XUZ4T7M","created_at":"2026-07-05T01:06:47Z"}],"graph_snapshots":[{"event_id":"sha256:86549538f37dedf8aab54edd8ca91032e21b582d791a6bee1f6f266f70e4f1a9","target":"graph","created_at":"2026-07-05T01:06:47Z","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/1905.13341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When function approximation is deployed in reinforcement learning (RL), the same problem may be formulated in different ways, often by treating a pre-processing step as a part of the environment or as part of the agent. As a consequence, fundamental concepts in RL, such as (optimal) value functions, are not uniquely defined as they depend on where we draw this agent-environment boundary, causing problems in theoretical analyses that provide optimality guarantees. We address this issue via a simple and novel boundary-invariant analysis of Fitted Q-Iteration, a representative RL algorithm, where","authors_text":"Nan Jiang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T22:39:57Z","title":"On Value Functions and the Agent-Environment Boundary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13341","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":"sha256:665b592fca7b6e49549ed579a9a1af2593ab1488856dc1b3e62a43415e1b13e0","target":"record","created_at":"2026-07-05T01:06:47Z","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":"46bd74bb16c349ebf171c6313764d1d9abe471601d455b63dfd64d4eb1876eb6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T22:39:57Z","title_canon_sha256":"99269deb6abfe8ed9eaa45d8e4e5a88893cc995919a669044fc6e33c56fb7633"},"schema_version":"1.0","source":{"id":"1905.13341","kind":"arxiv","version":3}},"canonical_sha256":"dde99e4fec58f8ce182a676b3570ad67c2ad42448efef7c036774b9b03025bcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dde99e4fec58f8ce182a676b3570ad67c2ad42448efef7c036774b9b03025bcc","first_computed_at":"2026-07-05T01:06:47.845952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:47.845952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldr47e4uyhJnUlTuL/2K8OSBdIMCyiGzTE5ynhQk4eA9W0eAfHLXSb2xXvG7QETEfDhbEB7GE2RVZS5aJy/dBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:47.846439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13341","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:665b592fca7b6e49549ed579a9a1af2593ab1488856dc1b3e62a43415e1b13e0","sha256:86549538f37dedf8aab54edd8ca91032e21b582d791a6bee1f6f266f70e4f1a9"],"state_sha256":"9cc3cccf563c4e82bf8291975bebb20dfe56d41265bcd09a3b0ec8e7784479d6"}