{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OEPJRJXJDTBGTSY2USYPXOC3IS","short_pith_number":"pith:OEPJRJXJ","canonical_record":{"source":{"id":"1806.04624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-12T16:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"10b9c6ede79f28ff6efe1064f33831e3775f068db87f30427aa38998fd1902c1","abstract_canon_sha256":"8191f2b62809c2cb40ff18ab46ff28696471b2198fb9b6acdee3a01ac0dba985"},"schema_version":"1.0"},"canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","source":{"kind":"arxiv","id":"1806.04624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04624","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04624v1","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04624","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"OEPJRJXJDTBG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OEPJRJXJDTBGTSY2","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OEPJRJXJ","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OEPJRJXJDTBGTSY2USYPXOC3IS","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-12T16:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"10b9c6ede79f28ff6efe1064f33831e3775f068db87f30427aa38998fd1902c1","abstract_canon_sha256":"8191f2b62809c2cb40ff18ab46ff28696471b2198fb9b6acdee3a01ac0dba985"},"schema_version":"1.0"},"canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:33.167811Z","signature_b64":"lQGRIOcLwL93bfJJn2Dva/hVtzuIDrwtwbtpMchv5ss6Pv5RwAkyqXFO3bQHCrhOTr2pS0uILf0GoF6l5M8wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","last_reissued_at":"2026-05-18T00:13:33.167351Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:33.167351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04624","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":"2026-05-18T00:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd+sHP7V4zxaqSDc1KdaDhiqA1J/aLv1I8/iRDiMwU6R8ZREMPN8sE83wVMrT9NyHiYW0TGrN3lEkF/4pwfwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:25:09.863180Z"},"content_sha256":"2bf6256e201f8b6351a8ebb694bbb755534272535e3e7e8c28c87df6160164c4","schema_version":"1.0","event_id":"sha256:2bf6256e201f8b6351a8ebb694bbb755534272535e3e7e8c28c87df6160164c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OEPJRJXJDTBGTSY2USYPXOC3IS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam White, Andrew Patterson, Martha White, Muhammad Zaheer, Yangchen Pan","submitted_at":"2018-06-12T16:07:31Z","abstract_excerpt":"Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one-step experience to update the action-value function. This elegant planning strategy has been mostly explored in the tabular setting. The aim of this paper is to revisit sample-based planning, in stochastic and continuous domains with learned models. We first highlight the flexibility afforded by a model over Experience Replay (ER). Replay-based methods can be seen as stochastic planning methods that repeatedly sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04624","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":"2026-05-18T00:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EgV+0yd1i4zyYdfiZtLQ2szaOVskDk9pH62P9VlbrsUKZT13TTZhMuqzX6IVlRKei+m8eVf5KiqJXA7CZdyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:25:09.863896Z"},"content_sha256":"0673c82b67489fd7b46f59443728cdb56576bffe44d6ebedad346f941fae8093","schema_version":"1.0","event_id":"sha256:0673c82b67489fd7b46f59443728cdb56576bffe44d6ebedad346f941fae8093"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/bundle.json","state_url":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/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":"2026-05-25T16:25:09Z","links":{"resolver":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS","bundle":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/bundle.json","state":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OEPJRJXJDTBGTSY2USYPXOC3IS","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":"8191f2b62809c2cb40ff18ab46ff28696471b2198fb9b6acdee3a01ac0dba985","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-12T16:07:31Z","title_canon_sha256":"10b9c6ede79f28ff6efe1064f33831e3775f068db87f30427aa38998fd1902c1"},"schema_version":"1.0","source":{"id":"1806.04624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04624","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04624v1","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04624","created_at":"2026-05-18T00:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"OEPJRJXJDTBG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OEPJRJXJDTBGTSY2","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OEPJRJXJ","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:0673c82b67489fd7b46f59443728cdb56576bffe44d6ebedad346f941fae8093","target":"graph","created_at":"2026-05-18T00:13:33Z","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":"Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one-step experience to update the action-value function. This elegant planning strategy has been mostly explored in the tabular setting. The aim of this paper is to revisit sample-based planning, in stochastic and continuous domains with learned models. We first highlight the flexibility afforded by a model over Experience Replay (ER). Replay-based methods can be seen as stochastic planning methods that repeatedly sampl","authors_text":"Adam White, Andrew Patterson, Martha White, Muhammad Zaheer, Yangchen Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-12T16:07:31Z","title":"Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04624","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":"sha256:2bf6256e201f8b6351a8ebb694bbb755534272535e3e7e8c28c87df6160164c4","target":"record","created_at":"2026-05-18T00:13:33Z","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":"8191f2b62809c2cb40ff18ab46ff28696471b2198fb9b6acdee3a01ac0dba985","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-12T16:07:31Z","title_canon_sha256":"10b9c6ede79f28ff6efe1064f33831e3775f068db87f30427aa38998fd1902c1"},"schema_version":"1.0","source":{"id":"1806.04624","kind":"arxiv","version":1}},"canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","first_computed_at":"2026-05-18T00:13:33.167351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:33.167351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lQGRIOcLwL93bfJJn2Dva/hVtzuIDrwtwbtpMchv5ss6Pv5RwAkyqXFO3bQHCrhOTr2pS0uILf0GoF6l5M8wBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:33.167811Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bf6256e201f8b6351a8ebb694bbb755534272535e3e7e8c28c87df6160164c4","sha256:0673c82b67489fd7b46f59443728cdb56576bffe44d6ebedad346f941fae8093"],"state_sha256":"dc6588417142a1166663c8772c116ae426303607b1c61bf88ab4b342599236f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ba91rqpkV4cHnDGvyAQeOnmG1g/6kMIQOCYVtNwNHsTF59HI8FTA/d02FtOOSSSkqardrzb5KCsYKdu//DXJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:25:09.867743Z","bundle_sha256":"8ec377e02cb7f0ccfdc2cffb3430e37984d02b4e34ae70fb0a88d2b4b30d45d7"}}