{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6UQC5DEMEJX3DE4YXLUAPEZIBX","short_pith_number":"pith:6UQC5DEM","canonical_record":{"source":{"id":"1912.07544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T17:47:57Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"3ae8a88dbebc4fa2caae5f76f506c754fac9856a244bef9d09889a9e9b8f288e","abstract_canon_sha256":"05669d6dbe83b03d60af1e5b8e99dcf3326f383674672248dc139a91dcb5f086"},"schema_version":"1.0"},"canonical_sha256":"f5202e8c8c226fb19398bae80793280dd0144c40a61ae5759277892bf7418af7","source":{"kind":"arxiv","id":"1912.07544","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07544","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07544v2","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07544","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"6UQC5DEMEJX3","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"6UQC5DEMEJX3DE4Y","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"6UQC5DEM","created_at":"2026-07-05T01:09:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6UQC5DEMEJX3DE4YXLUAPEZIBX","target":"record","payload":{"canonical_record":{"source":{"id":"1912.07544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T17:47:57Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"3ae8a88dbebc4fa2caae5f76f506c754fac9856a244bef9d09889a9e9b8f288e","abstract_canon_sha256":"05669d6dbe83b03d60af1e5b8e99dcf3326f383674672248dc139a91dcb5f086"},"schema_version":"1.0"},"canonical_sha256":"f5202e8c8c226fb19398bae80793280dd0144c40a61ae5759277892bf7418af7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:40.079215Z","signature_b64":"XM6iyIa7hA8ZEA7A1jK5FceAxOJHzjbeT/0XFpLZxlKtsILEMwuDnWUlo/npz4d3PIYOymfUhBPPwv5h/8vLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5202e8c8c226fb19398bae80793280dd0144c40a61ae5759277892bf7418af7","last_reissued_at":"2026-07-05T01:09:40.078760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:40.078760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.07544","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L9ZIt5Bp35vW+NmErPTL25IswblemKIBnrkjweoJoV8mKAf8TzhYIc5QVOV6fsPYFz7wEwiFKTXSBb4xfCWLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:15:03.416755Z"},"content_sha256":"673a59dd3fbe6e51ad6ae8176ea0e9f829dfee728c5ba570d5eb522b5ee7e046","schema_version":"1.0","event_id":"sha256:673a59dd3fbe6e51ad6ae8176ea0e9f829dfee728c5ba570d5eb522b5ee7e046"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6UQC5DEMEJX3DE4YXLUAPEZIBX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning with Abstract Learned Models While Learning Transferable Subtasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Matuszek, Erebus Oh, John Winder, Marie desJardins, Matthew Landen, Shane Parr, Shawn Squire, Stephanie Milani","submitted_at":"2019-12-16T17:47:57Z","abstract_excerpt":"We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07544","kind":"arxiv","version":2},"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/1912.07544/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":"2026-07-05T01:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNatWeqT+jyhRP3RKAtpvvQUzy+5kPzZNodJ4OCJuqUcS1td0HHlvEkXx4ToWtuVIRhQ4QAsSPRayWanDDIwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:15:03.417133Z"},"content_sha256":"f8773354a41c8e669f2f7e3a9dbd4a04d082007da21574fbab461cddd018d629","schema_version":"1.0","event_id":"sha256:f8773354a41c8e669f2f7e3a9dbd4a04d082007da21574fbab461cddd018d629"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/bundle.json","state_url":"https://pith.science/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/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":"2026-07-07T11:15:03Z","links":{"resolver":"https://pith.science/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX","bundle":"https://pith.science/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/bundle.json","state":"https://pith.science/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UQC5DEMEJX3DE4YXLUAPEZIBX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6UQC5DEMEJX3DE4YXLUAPEZIBX","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":"05669d6dbe83b03d60af1e5b8e99dcf3326f383674672248dc139a91dcb5f086","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T17:47:57Z","title_canon_sha256":"3ae8a88dbebc4fa2caae5f76f506c754fac9856a244bef9d09889a9e9b8f288e"},"schema_version":"1.0","source":{"id":"1912.07544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07544","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07544v2","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07544","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"6UQC5DEMEJX3","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"6UQC5DEMEJX3DE4Y","created_at":"2026-07-05T01:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"6UQC5DEM","created_at":"2026-07-05T01:09:40Z"}],"graph_snapshots":[{"event_id":"sha256:f8773354a41c8e669f2f7e3a9dbd4a04d082007da21574fbab461cddd018d629","target":"graph","created_at":"2026-07-05T01:09:40Z","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/1912.07544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical model","authors_text":"Cynthia Matuszek, Erebus Oh, John Winder, Marie desJardins, Matthew Landen, Shane Parr, Shawn Squire, Stephanie Milani","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T17:47:57Z","title":"Planning with Abstract Learned Models While Learning Transferable Subtasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07544","kind":"arxiv","version":2},"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":"sha256:673a59dd3fbe6e51ad6ae8176ea0e9f829dfee728c5ba570d5eb522b5ee7e046","target":"record","created_at":"2026-07-05T01:09:40Z","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":"05669d6dbe83b03d60af1e5b8e99dcf3326f383674672248dc139a91dcb5f086","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-16T17:47:57Z","title_canon_sha256":"3ae8a88dbebc4fa2caae5f76f506c754fac9856a244bef9d09889a9e9b8f288e"},"schema_version":"1.0","source":{"id":"1912.07544","kind":"arxiv","version":2}},"canonical_sha256":"f5202e8c8c226fb19398bae80793280dd0144c40a61ae5759277892bf7418af7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5202e8c8c226fb19398bae80793280dd0144c40a61ae5759277892bf7418af7","first_computed_at":"2026-07-05T01:09:40.078760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:40.078760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XM6iyIa7hA8ZEA7A1jK5FceAxOJHzjbeT/0XFpLZxlKtsILEMwuDnWUlo/npz4d3PIYOymfUhBPPwv5h/8vLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:40.079215Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.07544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:673a59dd3fbe6e51ad6ae8176ea0e9f829dfee728c5ba570d5eb522b5ee7e046","sha256:f8773354a41c8e669f2f7e3a9dbd4a04d082007da21574fbab461cddd018d629"],"state_sha256":"7977540a0098c5473a895cd6401c7f29200d45ed3dd95908ea441a64ee398a12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZ+2ReumPQ5J1bma+ewwac1p6WR/Ko5iARSHrxQpkLy7gDJLGpIs46NcO6nt9GJGJYK6TZR0zEbBGs+Bop50Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:15:03.419184Z","bundle_sha256":"7aa6d76828956f3e9e9e6ddfe96efd74ac225097b783da69f85d2a51c029c89b"}}