{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GXYEIQ777BYEGYV7FCTARIF4AB","short_pith_number":"pith:GXYEIQ77","schema_version":"1.0","canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","source":{"kind":"arxiv","id":"2006.05595","version":1},"attestation_state":"computed","paper":{"title":"Fitted Q-Learning for Relational Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kaushik Roy, Kristian Kersting, Ronald Parr, Srijita Das, Sriraam Natarajan","submitted_at":"2020-06-10T01:18:47Z","abstract_excerpt":"We consider the problem of Approximate Dynamic Programming in relational domains. Inspired by the success of fitted Q-learning methods in propositional settings, we develop the first relational fitted Q-learning algorithms by representing the value function and Bellman residuals. When we fit the Q-functions, we show how the two steps of Bellman operator; application and projection steps can be performed using a gradient-boosting technique. Our proposed framework performs reasonably well on standard domains without using domain models and using fewer training trajectories."},"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":"2006.05595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T01:18:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b7d1e4fd1e6ab670140a148a990a3a9756dfea328b730e66d68916b1bc44d5f","abstract_canon_sha256":"b4dc7d13326d4f0ea4376438ae212ef86d4f2a0c04b81cdce969f3a5096e0eba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:14.988246Z","signature_b64":"48pomD8hW4pwwafu9UxNztjOrMJLlTlEkHNNRjpcQzx0SvOSwzMumTghOJBDF4zrYKbqHaJ2niWhJEG3X6pLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","last_reissued_at":"2026-07-05T01:09:14.987906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:14.987906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fitted Q-Learning for Relational Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kaushik Roy, Kristian Kersting, Ronald Parr, Srijita Das, Sriraam Natarajan","submitted_at":"2020-06-10T01:18:47Z","abstract_excerpt":"We consider the problem of Approximate Dynamic Programming in relational domains. Inspired by the success of fitted Q-learning methods in propositional settings, we develop the first relational fitted Q-learning algorithms by representing the value function and Bellman residuals. When we fit the Q-functions, we show how the two steps of Bellman operator; application and projection steps can be performed using a gradient-boosting technique. Our proposed framework performs reasonably well on standard domains without using domain models and using fewer training trajectories."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05595","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/2006.05595/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":"2006.05595","created_at":"2026-07-05T01:09:14.987960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05595v1","created_at":"2026-07-05T01:09:14.987960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05595","created_at":"2026-07-05T01:09:14.987960+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXYEIQ777BYE","created_at":"2026-07-05T01:09:14.987960+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXYEIQ777BYEGYV7","created_at":"2026-07-05T01:09:14.987960+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXYEIQ77","created_at":"2026-07-05T01:09:14.987960+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/GXYEIQ777BYEGYV7FCTARIF4AB","json":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB.json","graph_json":"https://pith.science/api/pith-number/GXYEIQ777BYEGYV7FCTARIF4AB/graph.json","events_json":"https://pith.science/api/pith-number/GXYEIQ777BYEGYV7FCTARIF4AB/events.json","paper":"https://pith.science/paper/GXYEIQ77"},"agent_actions":{"view_html":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB","download_json":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB.json","view_paper":"https://pith.science/paper/GXYEIQ77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05595&json=true","fetch_graph":"https://pith.science/api/pith-number/GXYEIQ777BYEGYV7FCTARIF4AB/graph.json","fetch_events":"https://pith.science/api/pith-number/GXYEIQ777BYEGYV7FCTARIF4AB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/action/storage_attestation","attest_author":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/action/author_attestation","sign_citation":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/action/citation_signature","submit_replication":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/action/replication_record"}},"created_at":"2026-07-05T01:09:14.987960+00:00","updated_at":"2026-07-05T01:09:14.987960+00:00"}