{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JPG53CJL4HYL4XAJZ5OY4BXW5B","short_pith_number":"pith:JPG53CJL","canonical_record":{"source":{"id":"1906.05243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T16:57:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"41a3cdbb07ef3bf4d59f7b35393b95f6728282c17c5e08888d7cd45707c1f0f7","abstract_canon_sha256":"2fd1b2ef33a9f6aa60f069e71708303197e56a8263a1b9a59c45a75a94fd6c6a"},"schema_version":"1.0"},"canonical_sha256":"4bcddd892be1f0be5c09cf5d8e06f6e869efcf3bef54cf57afc37b01c9f1883a","source":{"kind":"arxiv","id":"1906.05243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05243","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05243v1","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05243","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"JPG53CJL4HYL","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"JPG53CJL4HYL4XAJ","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"JPG53CJL","created_at":"2026-07-05T00:04:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JPG53CJL4HYL4XAJZ5OY4BXW5B","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T16:57:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"41a3cdbb07ef3bf4d59f7b35393b95f6728282c17c5e08888d7cd45707c1f0f7","abstract_canon_sha256":"2fd1b2ef33a9f6aa60f069e71708303197e56a8263a1b9a59c45a75a94fd6c6a"},"schema_version":"1.0"},"canonical_sha256":"4bcddd892be1f0be5c09cf5d8e06f6e869efcf3bef54cf57afc37b01c9f1883a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:56.431305Z","signature_b64":"pv2he8dPJ1T2zFQwuQV1YkWI/q25454YP891DvLxZ2EPTvgALUQeaxzAIvbSh+PYlHniKg0PV9fxQV4wiqLtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bcddd892be1f0be5c09cf5d8e06f6e869efcf3bef54cf57afc37b01c9f1883a","last_reissued_at":"2026-07-05T00:04:56.430816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:56.430816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05243","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":"2026-07-05T00:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PX5w7wCEpWh70UKx9XMXLBsOSIy2ho7tWvGn4PnO382ktGBRaw6u0ybAT805cen+cvepjxgl1I64cDZajw6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:18:21.131511Z"},"content_sha256":"4910e78e0b1236b208c96a854d30ae3cde5f295d058dd01684367db30577437c","schema_version":"1.0","event_id":"sha256:4910e78e0b1236b208c96a854d30ae3cde5f295d058dd01684367db30577437c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JPG53CJL4HYL4XAJZ5OY4BXW5B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When to use parametric models in reinforcement learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, John Aslanides, Matteo Hessel","submitted_at":"2019-06-12T16:57:00Z","abstract_excerpt":"We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan: to use more computation without additional data to improve predictions and behaviour. We discuss when to expect benefits from either approach, and interpret prior work in this context. We hypothesise that, under suitable conditions, replay-based algorithms should be competitive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05243","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/1906.05243/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":"2026-07-05T00:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sgmYVtp1b9iQzk2zWbbx0Jth9Hlg6S9+RtVkGDzCM0YPS/tQX2jJ/zmYG1Jxwnn3H3U2ZyRkWYl6sq5mqtuICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:18:21.132715Z"},"content_sha256":"20231a70ce4cf32dfd6e9d8333358b6dee41447da9ddfd555c9d770221f97504","schema_version":"1.0","event_id":"sha256:20231a70ce4cf32dfd6e9d8333358b6dee41447da9ddfd555c9d770221f97504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/bundle.json","state_url":"https://pith.science/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/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":"2026-08-21T17:18:21Z","links":{"resolver":"https://pith.science/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B","bundle":"https://pith.science/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/bundle.json","state":"https://pith.science/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPG53CJL4HYL4XAJZ5OY4BXW5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JPG53CJL4HYL4XAJZ5OY4BXW5B","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":"2fd1b2ef33a9f6aa60f069e71708303197e56a8263a1b9a59c45a75a94fd6c6a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T16:57:00Z","title_canon_sha256":"41a3cdbb07ef3bf4d59f7b35393b95f6728282c17c5e08888d7cd45707c1f0f7"},"schema_version":"1.0","source":{"id":"1906.05243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05243","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05243v1","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05243","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"JPG53CJL4HYL","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"JPG53CJL4HYL4XAJ","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"JPG53CJL","created_at":"2026-07-05T00:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:20231a70ce4cf32dfd6e9d8333358b6dee41447da9ddfd555c9d770221f97504","target":"graph","created_at":"2026-07-05T00:04:56Z","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/1906.05243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan: to use more computation without additional data to improve predictions and behaviour. We discuss when to expect benefits from either approach, and interpret prior work in this context. We hypothesise that, under suitable conditions, replay-based algorithms should be competitive","authors_text":"Hado van Hasselt, John Aslanides, Matteo Hessel","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T16:57:00Z","title":"When to use parametric models in reinforcement learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05243","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":"sha256:4910e78e0b1236b208c96a854d30ae3cde5f295d058dd01684367db30577437c","target":"record","created_at":"2026-07-05T00:04:56Z","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":"2fd1b2ef33a9f6aa60f069e71708303197e56a8263a1b9a59c45a75a94fd6c6a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T16:57:00Z","title_canon_sha256":"41a3cdbb07ef3bf4d59f7b35393b95f6728282c17c5e08888d7cd45707c1f0f7"},"schema_version":"1.0","source":{"id":"1906.05243","kind":"arxiv","version":1}},"canonical_sha256":"4bcddd892be1f0be5c09cf5d8e06f6e869efcf3bef54cf57afc37b01c9f1883a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bcddd892be1f0be5c09cf5d8e06f6e869efcf3bef54cf57afc37b01c9f1883a","first_computed_at":"2026-07-05T00:04:56.430816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:56.430816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pv2he8dPJ1T2zFQwuQV1YkWI/q25454YP891DvLxZ2EPTvgALUQeaxzAIvbSh+PYlHniKg0PV9fxQV4wiqLtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:56.431305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4910e78e0b1236b208c96a854d30ae3cde5f295d058dd01684367db30577437c","sha256:20231a70ce4cf32dfd6e9d8333358b6dee41447da9ddfd555c9d770221f97504"],"state_sha256":"7580d1000a545edce82b8f5268b6e95b36221fef0d38ef164920202cf69fc873"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8SaG+Iwi7MyIHGgqUKJfem9z5Cm8XOAHFsFlJVVtUWpUmWcqK6GL1E3A8ooJCl4i6lxqcDe/rDRL1zne1ns2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:18:21.141510Z","bundle_sha256":"f5b76ec9b5cbd08518e2d854ab8bae8b0de7195ef975710834cf2cda488a23b1"}}