{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:AMJZOUXQKMWOSC7NOHUXHGPNAB","short_pith_number":"pith:AMJZOUXQ","canonical_record":{"source":{"id":"1109.2156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-09T20:43:53Z","cross_cats_sorted":[],"title_canon_sha256":"5c2fedb2b70e1c09f0dffba7f5c7733d2ac3f45568ae1cd45867e2af701604e5","abstract_canon_sha256":"8655bde7ad079e9a87c2fed2e3e817fe76ae7140fd0de4308b5d704fb2d37258"},"schema_version":"1.0"},"canonical_sha256":"03139752f0532ce90bed71e97399ed0060a4323dfbf834919c22d8bd21456ad5","source":{"kind":"arxiv","id":"1109.2156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.2156","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"1109.2156v1","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.2156","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"AMJZOUXQKMWO","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"AMJZOUXQKMWOSC7N","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"AMJZOUXQ","created_at":"2026-05-18T12:26:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:AMJZOUXQKMWOSC7NOHUXHGPNAB","target":"record","payload":{"canonical_record":{"source":{"id":"1109.2156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-09T20:43:53Z","cross_cats_sorted":[],"title_canon_sha256":"5c2fedb2b70e1c09f0dffba7f5c7733d2ac3f45568ae1cd45867e2af701604e5","abstract_canon_sha256":"8655bde7ad079e9a87c2fed2e3e817fe76ae7140fd0de4308b5d704fb2d37258"},"schema_version":"1.0"},"canonical_sha256":"03139752f0532ce90bed71e97399ed0060a4323dfbf834919c22d8bd21456ad5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:13:38.409989Z","signature_b64":"rwFSZkLH98Mujz0+2MTDJ7CmXQ1BKD6M7vmyUnM4iVbAy9C+6Vfu16WRtXkbngSWnoOqOVtnRKl1IJZkjSGlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03139752f0532ce90bed71e97399ed0060a4323dfbf834919c22d8bd21456ad5","last_reissued_at":"2026-05-18T04:13:38.409494Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:13:38.409494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1109.2156","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":"2026-05-18T04:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfRRn3SBzfec71PhioAT4kfeOFDBvfQ5RVus2VyTlx7vt1lvpoM9vuNGf4qyztt2lQXXGPBHvLSTlgayUatgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:47:00.443464Z"},"content_sha256":"14111e5d842df08ebed5cdaedbcf570b8c024ecc598adb76ce3d5c359de18205","schema_version":"1.0","event_id":"sha256:14111e5d842df08ebed5cdaedbcf570b8c024ecc598adb76ce3d5c359de18205"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:AMJZOUXQKMWOSC7NOHUXHGPNAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Policy Iteration with a Policy Language Bias: Solving Relational Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"A. Fern, R. Givan, S. Yoon","submitted_at":"2011-09-09T20:43:53Z","abstract_excerpt":"We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy space. This is advantageous in domains where good policies are easier to represent and learn than the corresponding value functions, which is often the case for the relational MDPs we are interested in. In order to apply API to such problems, we introduce a relational policy language and corresponding learner. In addition, we introduce a new bootstrapping ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.2156","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":""},"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":"2026-05-18T04:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZEwliLi+5mbFtQ0REdU1s1PnibK5JL2iFkNu/RXiFBkjzWXVKbGitZXmM9kGyak3Bh0Pc5gX2hrmea/kj86AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T06:47:00.443818Z"},"content_sha256":"0e11bf3dd6177fdd4586e32a67cf4eaa7a09b5212a31e019a46736b664d207e8","schema_version":"1.0","event_id":"sha256:0e11bf3dd6177fdd4586e32a67cf4eaa7a09b5212a31e019a46736b664d207e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/bundle.json","state_url":"https://pith.science/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/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":"2026-06-03T06:47:00Z","links":{"resolver":"https://pith.science/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB","bundle":"https://pith.science/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/bundle.json","state":"https://pith.science/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMJZOUXQKMWOSC7NOHUXHGPNAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:AMJZOUXQKMWOSC7NOHUXHGPNAB","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":"8655bde7ad079e9a87c2fed2e3e817fe76ae7140fd0de4308b5d704fb2d37258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-09T20:43:53Z","title_canon_sha256":"5c2fedb2b70e1c09f0dffba7f5c7733d2ac3f45568ae1cd45867e2af701604e5"},"schema_version":"1.0","source":{"id":"1109.2156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.2156","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"1109.2156v1","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.2156","created_at":"2026-05-18T04:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"AMJZOUXQKMWO","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"AMJZOUXQKMWOSC7N","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"AMJZOUXQ","created_at":"2026-05-18T12:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:0e11bf3dd6177fdd4586e32a67cf4eaa7a09b5212a31e019a46736b664d207e8","target":"graph","created_at":"2026-05-18T04:13:38Z","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"},"paper":{"abstract_excerpt":"We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy space. This is advantageous in domains where good policies are easier to represent and learn than the corresponding value functions, which is often the case for the relational MDPs we are interested in. In order to apply API to such problems, we introduce a relational policy language and corresponding learner. In addition, we introduce a new bootstrapping ro","authors_text":"A. Fern, R. Givan, S. Yoon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-09T20:43:53Z","title":"Approximate Policy Iteration with a Policy Language Bias: Solving Relational Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.2156","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":"sha256:14111e5d842df08ebed5cdaedbcf570b8c024ecc598adb76ce3d5c359de18205","target":"record","created_at":"2026-05-18T04:13:38Z","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":"8655bde7ad079e9a87c2fed2e3e817fe76ae7140fd0de4308b5d704fb2d37258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-09T20:43:53Z","title_canon_sha256":"5c2fedb2b70e1c09f0dffba7f5c7733d2ac3f45568ae1cd45867e2af701604e5"},"schema_version":"1.0","source":{"id":"1109.2156","kind":"arxiv","version":1}},"canonical_sha256":"03139752f0532ce90bed71e97399ed0060a4323dfbf834919c22d8bd21456ad5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03139752f0532ce90bed71e97399ed0060a4323dfbf834919c22d8bd21456ad5","first_computed_at":"2026-05-18T04:13:38.409494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:13:38.409494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwFSZkLH98Mujz0+2MTDJ7CmXQ1BKD6M7vmyUnM4iVbAy9C+6Vfu16WRtXkbngSWnoOqOVtnRKl1IJZkjSGlDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:13:38.409989Z","signed_message":"canonical_sha256_bytes"},"source_id":"1109.2156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14111e5d842df08ebed5cdaedbcf570b8c024ecc598adb76ce3d5c359de18205","sha256:0e11bf3dd6177fdd4586e32a67cf4eaa7a09b5212a31e019a46736b664d207e8"],"state_sha256":"5708d96920f2be080f4291d491ecad3bda8cea32f59e558bf1f1d47a40596a22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXwYpDs1tz9+DIIKBVqNLZUwlhb7W3/mb4baPmqAfdh45i64UVXDlWHvwgBe4Eu9902vdPSRCMC82Sl7NTIiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T06:47:00.445850Z","bundle_sha256":"051fbc0002a3f06086037fe91bb0327454891c80049e274a955110872f6887f6"}}