{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ETXZIAHEJMAY3L4LDWFAQVKSK3","short_pith_number":"pith:ETXZIAHE","schema_version":"1.0","canonical_sha256":"24ef9400e44b018daf8b1d8a08555256caa41137f8624d96dca0c6503ab3943f","source":{"kind":"arxiv","id":"2111.01587","version":1},"attestation_state":"computed","paper":{"title":"Procedural Generalization by Planning with Self-Supervised World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ankesh Anand, Eszter V\\'ertes, Jacob Walker, Jessica B. Hamrick, Julian Schrittwieser, Sherjil Ozair, Th\\'eophane Weber, Yazhe Li","submitted_at":"2021-11-02T13:32:21Z","abstract_excerpt":"One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents is not well understood because existing work has focused on model-free agents when benchmarking generalization. Here, we explicitly measure the generalization ability of model-based agents in comparison to their model-free counterparts. We focus our analysis on MuZero (Schrittwieser et al., 2020), a powerful model-based agent, and evaluate its performance on "},"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":"2111.01587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T13:32:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35228e3ea8453c45c0ac4cc456d08acba66f47bb81438e9e814e7a492b1346a9","abstract_canon_sha256":"6128061272288779e2712a3958b52cfd903557320da592ff57d745d31e1e438e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:30.531946Z","signature_b64":"5ZcmZMi+1/WjUg4L5RtABgfHE/SbPCTeog4l0W+aKcE1AjcaUUzx1EK15DE68qINqvw72k1L7YFGF7VMd3LvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ef9400e44b018daf8b1d8a08555256caa41137f8624d96dca0c6503ab3943f","last_reissued_at":"2026-07-05T03:28:30.531471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:30.531471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Procedural Generalization by Planning with Self-Supervised World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ankesh Anand, Eszter V\\'ertes, Jacob Walker, Jessica B. Hamrick, Julian Schrittwieser, Sherjil Ozair, Th\\'eophane Weber, Yazhe Li","submitted_at":"2021-11-02T13:32:21Z","abstract_excerpt":"One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents is not well understood because existing work has focused on model-free agents when benchmarking generalization. Here, we explicitly measure the generalization ability of model-based agents in comparison to their model-free counterparts. We focus our analysis on MuZero (Schrittwieser et al., 2020), a powerful model-based agent, and evaluate its performance on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01587","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/2111.01587/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":"2111.01587","created_at":"2026-07-05T03:28:30.531530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01587v1","created_at":"2026-07-05T03:28:30.531530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01587","created_at":"2026-07-05T03:28:30.531530+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETXZIAHEJMAY","created_at":"2026-07-05T03:28:30.531530+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETXZIAHEJMAY3L4L","created_at":"2026-07-05T03:28:30.531530+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETXZIAHE","created_at":"2026-07-05T03:28:30.531530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20411","citing_title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3","json":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3.json","graph_json":"https://pith.science/api/pith-number/ETXZIAHEJMAY3L4LDWFAQVKSK3/graph.json","events_json":"https://pith.science/api/pith-number/ETXZIAHEJMAY3L4LDWFAQVKSK3/events.json","paper":"https://pith.science/paper/ETXZIAHE"},"agent_actions":{"view_html":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3","download_json":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3.json","view_paper":"https://pith.science/paper/ETXZIAHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01587&json=true","fetch_graph":"https://pith.science/api/pith-number/ETXZIAHEJMAY3L4LDWFAQVKSK3/graph.json","fetch_events":"https://pith.science/api/pith-number/ETXZIAHEJMAY3L4LDWFAQVKSK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3/action/storage_attestation","attest_author":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3/action/author_attestation","sign_citation":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3/action/citation_signature","submit_replication":"https://pith.science/pith/ETXZIAHEJMAY3L4LDWFAQVKSK3/action/replication_record"}},"created_at":"2026-07-05T03:28:30.531530+00:00","updated_at":"2026-07-05T03:28:30.531530+00:00"}