{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQBLH7FRBPHCKW6G2Q3GRBDO2K","short_pith_number":"pith:BQBLH7FR","schema_version":"1.0","canonical_sha256":"0c02b3fcb10bce255bc6d43668846ed29c685ce212e8b8a7ab43eaa36cd22ecc","source":{"kind":"arxiv","id":"2407.07333","version":3},"attestation_state":"computed","paper":{"title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Kirtland, Cameron Allen, Daniel Scott, George Konidaris, Michael L. Littman, Nicholas Petrocelli, Omer Gottesman, Ronald Parr, Ruo Yu Tao, Sam Lobel","submitted_at":"2024-07-10T03:04:20Z","abstract_excerpt":"Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to -- or knowledge of -- an underlying, unobservable state space. Our metric, the $\\lambda$-discrepancy, is the difference between two distinct temporal difference (TD) value est"},"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":"2407.07333","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T03:04:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1e5ba439ce8e377f2b517be15e25c3d7689d20593598eed77647026462e0fdf1","abstract_canon_sha256":"8ea8e5126ca3f99380e40a0164a1494c87d274fb11a3b4fac366918a83d02d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:34.718120Z","signature_b64":"QdBsST53xNN689bEG7o1/tWZEKgRDqzwQCUpx/I4qRzX/RPOi9hBB2BZfnSGaMcJVdOcKNQHKjiNoh3+55N7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c02b3fcb10bce255bc6d43668846ed29c685ce212e8b8a7ab43eaa36cd22ecc","last_reissued_at":"2026-07-05T09:35:34.717620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:34.717620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Kirtland, Cameron Allen, Daniel Scott, George Konidaris, Michael L. Littman, Nicholas Petrocelli, Omer Gottesman, Ronald Parr, Ruo Yu Tao, Sam Lobel","submitted_at":"2024-07-10T03:04:20Z","abstract_excerpt":"Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to -- or knowledge of -- an underlying, unobservable state space. Our metric, the $\\lambda$-discrepancy, is the difference between two distinct temporal difference (TD) value est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07333","kind":"arxiv","version":3},"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/2407.07333/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":"2407.07333","created_at":"2026-07-05T09:35:34.717678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07333v3","created_at":"2026-07-05T09:35:34.717678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07333","created_at":"2026-07-05T09:35:34.717678+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQBLH7FRBPHC","created_at":"2026-07-05T09:35:34.717678+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQBLH7FRBPHCKW6G","created_at":"2026-07-05T09:35:34.717678+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQBLH7FR","created_at":"2026-07-05T09:35:34.717678+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/BQBLH7FRBPHCKW6G2Q3GRBDO2K","json":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K.json","graph_json":"https://pith.science/api/pith-number/BQBLH7FRBPHCKW6G2Q3GRBDO2K/graph.json","events_json":"https://pith.science/api/pith-number/BQBLH7FRBPHCKW6G2Q3GRBDO2K/events.json","paper":"https://pith.science/paper/BQBLH7FR"},"agent_actions":{"view_html":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K","download_json":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K.json","view_paper":"https://pith.science/paper/BQBLH7FR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07333&json=true","fetch_graph":"https://pith.science/api/pith-number/BQBLH7FRBPHCKW6G2Q3GRBDO2K/graph.json","fetch_events":"https://pith.science/api/pith-number/BQBLH7FRBPHCKW6G2Q3GRBDO2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K/action/storage_attestation","attest_author":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K/action/author_attestation","sign_citation":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K/action/citation_signature","submit_replication":"https://pith.science/pith/BQBLH7FRBPHCKW6G2Q3GRBDO2K/action/replication_record"}},"created_at":"2026-07-05T09:35:34.717678+00:00","updated_at":"2026-07-05T09:35:34.717678+00:00"}