{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VFMCYBKHJISFQ4MMMSWTPGBVOZ","short_pith_number":"pith:VFMCYBKH","canonical_record":{"source":{"id":"1904.01191","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T03:25:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"54203f189015a3c4040c14e29091d123bd2e4d018d65ab8ef582896cb098625b","abstract_canon_sha256":"70b533fc4b7a1c28dfb81081a1f7db3913dded29c8d26549a727908fa99b6c62"},"schema_version":"1.0"},"canonical_sha256":"a9582c05474a2458718c64ad379835764bcda6fdc236c00d29fbd1fb4fc91175","source":{"kind":"arxiv","id":"1904.01191","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01191","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01191v4","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01191","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"VFMCYBKHJISF","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"VFMCYBKHJISFQ4MM","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"VFMCYBKH","created_at":"2026-07-05T01:23:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VFMCYBKHJISFQ4MMMSWTPGBVOZ","target":"record","payload":{"canonical_record":{"source":{"id":"1904.01191","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T03:25:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"54203f189015a3c4040c14e29091d123bd2e4d018d65ab8ef582896cb098625b","abstract_canon_sha256":"70b533fc4b7a1c28dfb81081a1f7db3913dded29c8d26549a727908fa99b6c62"},"schema_version":"1.0"},"canonical_sha256":"a9582c05474a2458718c64ad379835764bcda6fdc236c00d29fbd1fb4fc91175","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:21.794970Z","signature_b64":"iQN0p3QOBV3mvPqPbuIHLwUxjFXAk3ENS7oMeoCyz0mwM3bxYmp91NDhYNcaKykRJEfo9efIO6WyAOXjxdRYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9582c05474a2458718c64ad379835764bcda6fdc236c00d29fbd1fb4fc91175","last_reissued_at":"2026-07-05T01:23:21.794558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:21.794558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.01191","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SbVHtkDd/20r93LqhJxl+twbjeMhxkyb64402oPd+y6Oaebf+GCEZRa50lFNhWQJqykcpmD1FbGbJ0zmbkkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:01:41.256559Z"},"content_sha256":"89b7747271c8f6acd428d9b995fce8f09531d41ac2032af23497551e7794f7e7","schema_version":"1.0","event_id":"sha256:89b7747271c8f6acd428d9b995fce8f09531d41ac2032af23497551e7794f7e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VFMCYBKHJISFQ4MMMSWTPGBVOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning with Expectation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam White, Martha White, Richard S. Sutton, Yi Wan, Zaheer Abbas","submitted_at":"2019-04-02T03:25:25Z","abstract_excerpt":"Distribution and sample models are two popular model choices in model-based reinforcement learning (MBRL). However, learning these models can be intractable, particularly when the state and action spaces are large. Expectation models, on the other hand, are relatively easier to learn due to their compactness and have also been widely used for deterministic environments. For stochastic environments, it is not obvious how expectation models can be used for planning as they only partially characterize a distribution. In this paper, we propose a sound way of using approximate expectation models fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01191","kind":"arxiv","version":4},"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/1904.01191/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":"2026-07-05T01:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZvViOfKJf2kba+YupCrX6idCiZJs4DrJnT/Ce33VMpMUS328N7DlkOez8j8GLZp1kInogE7xmQN7E8MNlxLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:01:41.257441Z"},"content_sha256":"d4b7ff52855a49524d571a42cc370b77f390f599b492011555054aba6752d1f1","schema_version":"1.0","event_id":"sha256:d4b7ff52855a49524d571a42cc370b77f390f599b492011555054aba6752d1f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/bundle.json","state_url":"https://pith.science/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/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":"2026-08-07T00:01:41Z","links":{"resolver":"https://pith.science/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ","bundle":"https://pith.science/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/bundle.json","state":"https://pith.science/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFMCYBKHJISFQ4MMMSWTPGBVOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VFMCYBKHJISFQ4MMMSWTPGBVOZ","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":"70b533fc4b7a1c28dfb81081a1f7db3913dded29c8d26549a727908fa99b6c62","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T03:25:25Z","title_canon_sha256":"54203f189015a3c4040c14e29091d123bd2e4d018d65ab8ef582896cb098625b"},"schema_version":"1.0","source":{"id":"1904.01191","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01191","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01191v4","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01191","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"VFMCYBKHJISF","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"VFMCYBKHJISFQ4MM","created_at":"2026-07-05T01:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"VFMCYBKH","created_at":"2026-07-05T01:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:d4b7ff52855a49524d571a42cc370b77f390f599b492011555054aba6752d1f1","target":"graph","created_at":"2026-07-05T01:23:21Z","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/1904.01191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distribution and sample models are two popular model choices in model-based reinforcement learning (MBRL). However, learning these models can be intractable, particularly when the state and action spaces are large. Expectation models, on the other hand, are relatively easier to learn due to their compactness and have also been widely used for deterministic environments. For stochastic environments, it is not obvious how expectation models can be used for planning as they only partially characterize a distribution. In this paper, we propose a sound way of using approximate expectation models fo","authors_text":"Adam White, Martha White, Richard S. Sutton, Yi Wan, Zaheer Abbas","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T03:25:25Z","title":"Planning with Expectation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01191","kind":"arxiv","version":4},"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":"sha256:89b7747271c8f6acd428d9b995fce8f09531d41ac2032af23497551e7794f7e7","target":"record","created_at":"2026-07-05T01:23:21Z","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":"70b533fc4b7a1c28dfb81081a1f7db3913dded29c8d26549a727908fa99b6c62","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T03:25:25Z","title_canon_sha256":"54203f189015a3c4040c14e29091d123bd2e4d018d65ab8ef582896cb098625b"},"schema_version":"1.0","source":{"id":"1904.01191","kind":"arxiv","version":4}},"canonical_sha256":"a9582c05474a2458718c64ad379835764bcda6fdc236c00d29fbd1fb4fc91175","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9582c05474a2458718c64ad379835764bcda6fdc236c00d29fbd1fb4fc91175","first_computed_at":"2026-07-05T01:23:21.794558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:21.794558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQN0p3QOBV3mvPqPbuIHLwUxjFXAk3ENS7oMeoCyz0mwM3bxYmp91NDhYNcaKykRJEfo9efIO6WyAOXjxdRYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:21.794970Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01191","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89b7747271c8f6acd428d9b995fce8f09531d41ac2032af23497551e7794f7e7","sha256:d4b7ff52855a49524d571a42cc370b77f390f599b492011555054aba6752d1f1"],"state_sha256":"32f822cd918744bdc069c5a5543fdc60352d3bee3a217c17221a489a3620f0df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HM5sjOKb15mXvevqlnHpJsB2YUTcBfWQ2GuhaH9lWzBdWOReLDVwaoFNpYWVMeJsVSHR+MqHsAdf4GOx0GizCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:01:41.263104Z","bundle_sha256":"1045c4c4dac238ca785562e4a29e90034159ef7eee548431b616ab3744ad9e8a"}}