{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GXYEIQ777BYEGYV7FCTARIF4AB","short_pith_number":"pith:GXYEIQ77","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"},"canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","source":{"kind":"arxiv","id":"2006.05595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05595","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05595v1","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05595","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"GXYEIQ777BYE","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"GXYEIQ777BYEGYV7","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"GXYEIQ77","created_at":"2026-07-05T01:09:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GXYEIQ777BYEGYV7FCTARIF4AB","target":"record","payload":{"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"},"canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","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"},"source_kind":"arxiv","source_id":"2006.05595","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVT46oRAbmlguhkJCqrWSMLeR0a3qRP518tYx1o503etGaIbXoCAWHd5bzhVnxklDVrzu7gpGTtvBILX58hyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:39.398076Z"},"content_sha256":"d73ce5b961343cddb6de1ace95fcb7b790c6283f931709f71abb6e29ed582c3c","schema_version":"1.0","event_id":"sha256:d73ce5b961343cddb6de1ace95fcb7b790c6283f931709f71abb6e29ed582c3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GXYEIQ777BYEGYV7FCTARIF4AB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KY0BHexabOIN7oWU2E/yxcZ9YtC/Q3N3vYKE98nqP6YUTR7AOtClqyMypE6SLC5GOlXdyogL02tMZEpkOlxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:39.398467Z"},"content_sha256":"edc1bf261a0dba0a0e512125ea15e2851713102e87cf90ec111063801c5b1a75","schema_version":"1.0","event_id":"sha256:edc1bf261a0dba0a0e512125ea15e2851713102e87cf90ec111063801c5b1a75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/bundle.json","state_url":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXYEIQ777BYEGYV7FCTARIF4AB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T15:47:39Z","links":{"resolver":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB","bundle":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/bundle.json","state":"https://pith.science/pith/GXYEIQ777BYEGYV7FCTARIF4AB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXYEIQ777BYEGYV7FCTARIF4AB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GXYEIQ777BYEGYV7FCTARIF4AB","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":"b4dc7d13326d4f0ea4376438ae212ef86d4f2a0c04b81cdce969f3a5096e0eba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T01:18:47Z","title_canon_sha256":"4b7d1e4fd1e6ab670140a148a990a3a9756dfea328b730e66d68916b1bc44d5f"},"schema_version":"1.0","source":{"id":"2006.05595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05595","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05595v1","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05595","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"GXYEIQ777BYE","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"GXYEIQ777BYEGYV7","created_at":"2026-07-05T01:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"GXYEIQ77","created_at":"2026-07-05T01:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:edc1bf261a0dba0a0e512125ea15e2851713102e87cf90ec111063801c5b1a75","target":"graph","created_at":"2026-07-05T01:09:14Z","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/2006.05595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Kaushik Roy, Kristian Kersting, Ronald Parr, Srijita Das, Sriraam Natarajan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T01:18:47Z","title":"Fitted Q-Learning for Relational Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05595","kind":"arxiv","version":1},"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:d73ce5b961343cddb6de1ace95fcb7b790c6283f931709f71abb6e29ed582c3c","target":"record","created_at":"2026-07-05T01:09:14Z","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":"b4dc7d13326d4f0ea4376438ae212ef86d4f2a0c04b81cdce969f3a5096e0eba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T01:18:47Z","title_canon_sha256":"4b7d1e4fd1e6ab670140a148a990a3a9756dfea328b730e66d68916b1bc44d5f"},"schema_version":"1.0","source":{"id":"2006.05595","kind":"arxiv","version":1}},"canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35f04443fff8704362bf28a608a0bc0048ddc11379c5a609671cd24013579881","first_computed_at":"2026-07-05T01:09:14.987906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:14.987906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48pomD8hW4pwwafu9UxNztjOrMJLlTlEkHNNRjpcQzx0SvOSwzMumTghOJBDF4zrYKbqHaJ2niWhJEG3X6pLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:14.988246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d73ce5b961343cddb6de1ace95fcb7b790c6283f931709f71abb6e29ed582c3c","sha256:edc1bf261a0dba0a0e512125ea15e2851713102e87cf90ec111063801c5b1a75"],"state_sha256":"39ab8d8c14acc56ee8dce00254d67d9f507cc5eccfb7c4cb7a98b9b402e0537c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBmdiHTBl5vgYiaZnwPw86EsuDnYLe7OBQcwNqeXlYbxOpIF4h7CGU+HcL6UMiEVpyNY6payoFXbG4OGbldFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:47:39.401650Z","bundle_sha256":"4bad35c80fd498b3ace2c8e4e778da3322e66689bc8357e75ee544b8c09d760a"}}