{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DDYILVFS5GTG7BAV4XG2XACXWC","short_pith_number":"pith:DDYILVFS","schema_version":"1.0","canonical_sha256":"18f085d4b2e9a66f8415e5cdab8057b086dba0b7f99d53b508b4fbc0e4ae6efc","source":{"kind":"arxiv","id":"2206.04384","version":3},"attestation_state":"computed","paper":{"title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyao Zhu, Li Erran Li, Mohamed Elhoseiny","submitted_at":"2022-06-09T09:51:42Z","abstract_excerpt":"Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in the original environments can be difficult. Focusing on the offline RL setting, we aim to build a simple and discrete world model that abstracts the original environment. RL methods are applied to our world model instead of the environment data for simplified policy learning. Our world model, dubbed Value Memory Graph (VMG), is designed as a directed-graph-"},"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":"2206.04384","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T09:51:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ec48884e61a1edea8588596b9bfe3b4e45fb23d978ca7db665d33afeb9f2a5a","abstract_canon_sha256":"da1baef397757ff171104963e08001d41383df3120e47f671e500b730b9b1e81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:58.334889Z","signature_b64":"Hy/k3wTXIzPod/BRCvFfFLgVBQ4hjz+OuAIU9NMv1gfviQ01tbutFQvx4+ZcKdHIUBqJ53++ZR0ID7NxgsZnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18f085d4b2e9a66f8415e5cdab8057b086dba0b7f99d53b508b4fbc0e4ae6efc","last_reissued_at":"2026-07-05T06:05:58.334442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:58.334442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyao Zhu, Li Erran Li, Mohamed Elhoseiny","submitted_at":"2022-06-09T09:51:42Z","abstract_excerpt":"Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in the original environments can be difficult. Focusing on the offline RL setting, we aim to build a simple and discrete world model that abstracts the original environment. RL methods are applied to our world model instead of the environment data for simplified policy learning. Our world model, dubbed Value Memory Graph (VMG), is designed as a directed-graph-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04384","kind":"arxiv","version":3},"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/2206.04384/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.04384","created_at":"2026-07-05T06:05:58.334498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04384v3","created_at":"2026-07-05T06:05:58.334498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04384","created_at":"2026-07-05T06:05:58.334498+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDYILVFS5GTG","created_at":"2026-07-05T06:05:58.334498+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDYILVFS5GTG7BAV","created_at":"2026-07-05T06:05:58.334498+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDYILVFS","created_at":"2026-07-05T06:05:58.334498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC","json":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC.json","graph_json":"https://pith.science/api/pith-number/DDYILVFS5GTG7BAV4XG2XACXWC/graph.json","events_json":"https://pith.science/api/pith-number/DDYILVFS5GTG7BAV4XG2XACXWC/events.json","paper":"https://pith.science/paper/DDYILVFS"},"agent_actions":{"view_html":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC","download_json":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC.json","view_paper":"https://pith.science/paper/DDYILVFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04384&json=true","fetch_graph":"https://pith.science/api/pith-number/DDYILVFS5GTG7BAV4XG2XACXWC/graph.json","fetch_events":"https://pith.science/api/pith-number/DDYILVFS5GTG7BAV4XG2XACXWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC/action/storage_attestation","attest_author":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC/action/author_attestation","sign_citation":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC/action/citation_signature","submit_replication":"https://pith.science/pith/DDYILVFS5GTG7BAV4XG2XACXWC/action/replication_record"}},"created_at":"2026-07-05T06:05:58.334498+00:00","updated_at":"2026-07-05T06:05:58.334498+00:00"}