{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KW6TJEV45U4A47T4TJ6ZEEE26H","short_pith_number":"pith:KW6TJEV4","schema_version":"1.0","canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","source":{"kind":"arxiv","id":"2505.08988","version":1},"attestation_state":"computed","paper":{"title":"Generalization in Monitored Markov Decision Processes (Mon-MDPs)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Bowling, Montaser Mohammedalamen","submitted_at":"2025-05-13T21:58:25Z","abstract_excerpt":"Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world scenarios, rewards are not always observable, which can be modeled as a monitored Markov decision process (Mon-MDP). Prior work on Mon-MDPs have been limited to simple, tabular cases, restricting their applicability to real-world problems. This work explores Mon-MDPs using function approximation (FA) and investigates the challenges involved. We show that combining f"},"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":"2505.08988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T21:58:25Z","cross_cats_sorted":[],"title_canon_sha256":"5fa323d208da4d441f52562bbfbe8b238c5f83b786fefb3826f2c910c5446bdf","abstract_canon_sha256":"394f471f272436f81767de272321fa19bc73cfeeecdc7ec549231a345e4a0552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:48.326907Z","signature_b64":"c8E6ifSgkqRqODX3rJbhh+JDV6SoLGQD4flbDq74pMoA1oAu1SXnbNyLlviyTScUkwKx2g0G3RfWPDsoWbviBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55bd3492bced380e7e7c9a7d92109af1caa7a73aab53947ecf2a15fd0520866b","last_reissued_at":"2026-07-05T11:02:48.326506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:48.326506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization in Monitored Markov Decision Processes (Mon-MDPs)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Bowling, Montaser Mohammedalamen","submitted_at":"2025-05-13T21:58:25Z","abstract_excerpt":"Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world scenarios, rewards are not always observable, which can be modeled as a monitored Markov decision process (Mon-MDP). Prior work on Mon-MDPs have been limited to simple, tabular cases, restricting their applicability to real-world problems. This work explores Mon-MDPs using function approximation (FA) and investigates the challenges involved. We show that combining f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08988","kind":"arxiv","version":1},"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/2505.08988/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":"2505.08988","created_at":"2026-07-05T11:02:48.326564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08988v1","created_at":"2026-07-05T11:02:48.326564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08988","created_at":"2026-07-05T11:02:48.326564+00:00"},{"alias_kind":"pith_short_12","alias_value":"KW6TJEV45U4A","created_at":"2026-07-05T11:02:48.326564+00:00"},{"alias_kind":"pith_short_16","alias_value":"KW6TJEV45U4A47T4","created_at":"2026-07-05T11:02:48.326564+00:00"},{"alias_kind":"pith_short_8","alias_value":"KW6TJEV4","created_at":"2026-07-05T11:02:48.326564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H","json":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H.json","graph_json":"https://pith.science/api/pith-number/KW6TJEV45U4A47T4TJ6ZEEE26H/graph.json","events_json":"https://pith.science/api/pith-number/KW6TJEV45U4A47T4TJ6ZEEE26H/events.json","paper":"https://pith.science/paper/KW6TJEV4"},"agent_actions":{"view_html":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H","download_json":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H.json","view_paper":"https://pith.science/paper/KW6TJEV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08988&json=true","fetch_graph":"https://pith.science/api/pith-number/KW6TJEV45U4A47T4TJ6ZEEE26H/graph.json","fetch_events":"https://pith.science/api/pith-number/KW6TJEV45U4A47T4TJ6ZEEE26H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/action/storage_attestation","attest_author":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/action/author_attestation","sign_citation":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/action/citation_signature","submit_replication":"https://pith.science/pith/KW6TJEV45U4A47T4TJ6ZEEE26H/action/replication_record"}},"created_at":"2026-07-05T11:02:48.326564+00:00","updated_at":"2026-07-05T11:02:48.326564+00:00"}