{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OEPJRJXJDTBGTSY2USYPXOC3IS","short_pith_number":"pith:OEPJRJXJ","schema_version":"1.0","canonical_sha256":"711e98a6e91cc269cb1aa4b0fbb85b44b5f8007a24eb347ead887fb1f17c14d8","source":{"kind":"arxiv","id":"1806.04624","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.04624","created_at":"2026-05-18T00:13:33.167418+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04624v1","created_at":"2026-05-18T00:13:33.167418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04624","created_at":"2026-05-18T00:13:33.167418+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEPJRJXJDTBG","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEPJRJXJDTBGTSY2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEPJRJXJ","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2006.04363","citing_title":"Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS","json":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS.json","graph_json":"https://pith.science/api/pith-number/OEPJRJXJDTBGTSY2USYPXOC3IS/graph.json","events_json":"https://pith.science/api/pith-number/OEPJRJXJDTBGTSY2USYPXOC3IS/events.json","paper":"https://pith.science/paper/OEPJRJXJ"},"agent_actions":{"view_html":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS","download_json":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS.json","view_paper":"https://pith.science/paper/OEPJRJXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04624&json=true","fetch_graph":"https://pith.science/api/pith-number/OEPJRJXJDTBGTSY2USYPXOC3IS/graph.json","fetch_events":"https://pith.science/api/pith-number/OEPJRJXJDTBGTSY2USYPXOC3IS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/action/storage_attestation","attest_author":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/action/author_attestation","sign_citation":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/action/citation_signature","submit_replication":"https://pith.science/pith/OEPJRJXJDTBGTSY2USYPXOC3IS/action/replication_record"}},"created_at":"2026-05-18T00:13:33.167418+00:00","updated_at":"2026-05-18T00:13:33.167418+00:00"}