{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5225D37VPNIMBVLMHXYVOR22HX","short_pith_number":"pith:5225D37V","canonical_record":{"source":{"id":"1802.09081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"c4beaa4f62a1117d8bcf04072b688b1dbfae93dfa97ef68b94e8425ae634d867","abstract_canon_sha256":"5ac7d2b91d911dfd2f770f877dabc6eef6d1342362be58a7b3c0e43d63ea9ac3"},"schema_version":"1.0"},"canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","source":{"kind":"arxiv","id":"1802.09081","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09081","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09081v2","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09081","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"5225D37VPNIM","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"5225D37VPNIMBVLM","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"5225D37V","created_at":"2026-07-05T00:42:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5225D37VPNIMBVLMHXYVOR22HX","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","cross_cats_sorted":[],"title_canon_sha256":"c4beaa4f62a1117d8bcf04072b688b1dbfae93dfa97ef68b94e8425ae634d867","abstract_canon_sha256":"5ac7d2b91d911dfd2f770f877dabc6eef6d1342362be58a7b3c0e43d63ea9ac3"},"schema_version":"1.0"},"canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:57.946078Z","signature_b64":"iEnI84ilsm5dCD81L8gvOCl48QIfKD6UA5t3h+N3mRhRkHB7KT8hIIlnNXXlofwNuCF/+Go7QUsj4jhG/LXzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","last_reissued_at":"2026-07-05T00:42:57.945600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:57.945600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09081","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":"2026-07-05T00:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVspzb2ZNzgPCV/ZnmP1SSgfsSq+NK48N5WC4zfYMxyJKmWK7Qrnokt0zRCDCbgWKNqOahleT4iasfFV3chXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:50:40.490532Z"},"content_sha256":"8bd2425e0e871652a567884b2ec59006117f8de7022dc022a09431e35733f342","schema_version":"1.0","event_id":"sha256:8bd2425e0e871652a567884b2ec59006117f8de7022dc022a09431e35733f342"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5225D37VPNIMBVLMHXYVOR22HX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Murtaza Dalal, Sergey Levine, Shixiang Gu, Vitchyr Pong","submitted_at":"2018-02-25T21:14:44Z","abstract_excerpt":"Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such as Q-learning. A limiting factor in classic model-free RL is that the learning signal consists only of scalar rewards, ignoring much of the rich information contained in state transition tuples. Model-based RL uses this information, by training a predictive model, but often does not achieve the same asymptotic performance as model-free RL due to model bias."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09081","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/1802.09081/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":"2026-07-05T00:42:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdhEvSH5lnKHiGK2mgZdHwfXEGcIH/ZgUKWYKiTtiPCbPipwOj3ZAKtLXth1aUSevGonf2kgj3fHMJ1MmIcBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:50:40.491060Z"},"content_sha256":"a363d46c09b9fbd8e6642a39f22282bbf122daf72442a27ab44e0471d56305fa","schema_version":"1.0","event_id":"sha256:a363d46c09b9fbd8e6642a39f22282bbf122daf72442a27ab44e0471d56305fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/bundle.json","state_url":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5225D37VPNIMBVLMHXYVOR22HX/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":"2026-08-08T02:50:40Z","links":{"resolver":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX","bundle":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/bundle.json","state":"https://pith.science/pith/5225D37VPNIMBVLMHXYVOR22HX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5225D37VPNIMBVLMHXYVOR22HX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5225D37VPNIMBVLMHXYVOR22HX","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":"5ac7d2b91d911dfd2f770f877dabc6eef6d1342362be58a7b3c0e43d63ea9ac3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","title_canon_sha256":"c4beaa4f62a1117d8bcf04072b688b1dbfae93dfa97ef68b94e8425ae634d867"},"schema_version":"1.0","source":{"id":"1802.09081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09081","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09081v2","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09081","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"5225D37VPNIM","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"5225D37VPNIMBVLM","created_at":"2026-07-05T00:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"5225D37V","created_at":"2026-07-05T00:42:57Z"}],"graph_snapshots":[{"event_id":"sha256:a363d46c09b9fbd8e6642a39f22282bbf122daf72442a27ab44e0471d56305fa","target":"graph","created_at":"2026-07-05T00:42:57Z","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/1802.09081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-free reinforcement learning (RL) is a powerful, general tool for learning complex behaviors. However, its sample efficiency is often impractically large for solving challenging real-world problems, even with off-policy algorithms such as Q-learning. A limiting factor in classic model-free RL is that the learning signal consists only of scalar rewards, ignoring much of the rich information contained in state transition tuples. Model-based RL uses this information, by training a predictive model, but often does not achieve the same asymptotic performance as model-free RL due to model bias.","authors_text":"Murtaza Dalal, Sergey Levine, Shixiang Gu, Vitchyr Pong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09081","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":"sha256:8bd2425e0e871652a567884b2ec59006117f8de7022dc022a09431e35733f342","target":"record","created_at":"2026-07-05T00:42:57Z","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":"5ac7d2b91d911dfd2f770f877dabc6eef6d1342362be58a7b3c0e43d63ea9ac3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-25T21:14:44Z","title_canon_sha256":"c4beaa4f62a1117d8bcf04072b688b1dbfae93dfa97ef68b94e8425ae634d867"},"schema_version":"1.0","source":{"id":"1802.09081","kind":"arxiv","version":2}},"canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeb5d1eff57b50c0d56c3df157475a3dd1d032326c996d75b0c70d154fff559d","first_computed_at":"2026-07-05T00:42:57.945600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:57.945600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iEnI84ilsm5dCD81L8gvOCl48QIfKD6UA5t3h+N3mRhRkHB7KT8hIIlnNXXlofwNuCF/+Go7QUsj4jhG/LXzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:57.946078Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bd2425e0e871652a567884b2ec59006117f8de7022dc022a09431e35733f342","sha256:a363d46c09b9fbd8e6642a39f22282bbf122daf72442a27ab44e0471d56305fa"],"state_sha256":"9e40dc845a56880e7e007f1cee7810cc557cf66d2fb61d621724312d485d5b76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2D9BirhLK24ojGX8o0v7m5dWZTRkABI5BJxfr/bLz4OYR8ZZmSAYF6hC0KQC4v08nqlu6z8tHUyXf8vTyZLCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:50:40.494831Z","bundle_sha256":"cb98067e7d3f2ba79368f1a90220a68e645583b170f9620fa9962da6f01ff6a8"}}