{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TRDHATQSROREFI3BYIUSNN43KV","short_pith_number":"pith:TRDHATQS","schema_version":"1.0","canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","source":{"kind":"arxiv","id":"2210.12719","version":1},"attestation_state":"computed","paper":{"title":"Learning General World Models in a Handful of Reward-Free Deployments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Edward Grefenstette, Jack Parker-Holder, Oleh Rybkin, Philip J. Ball, Stephen J. Roberts, Tim Rockt\\\"aschel, Yingchen Xu","submitted_at":"2022-10-23T12:38:03Z","abstract_excerpt":"Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to facilitate scalability, exploration policies should collect large quantities of data without costly centralized retraining. Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research. We then present CASCADE, a novel approach for self-supervised exploration in this new setting. CASCADE seeks to "},"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":"2210.12719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T12:38:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98ec5a63f019d154eb2860719b4dd7cb1a39c3ead4444f053b24a973e905895b","abstract_canon_sha256":"59c2efdaca34f452ad2879d2f55a679e90d10d2355f7a09ea4a3b638b3eacb06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:32.026713Z","signature_b64":"MApUYqMUg7JBwm+U06E0xl5+qQNUqf+ksFTxClaCK2XnEoDcAkjPA/xcrPpr9iK3RKsy9sqxpAhi7YDpyX4gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c46704e128ba242a361c22926b79b557136c2ef90c87563256319ee939538ac","last_reissued_at":"2026-07-05T05:09:32.026208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:32.026208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning General World Models in a Handful of Reward-Free Deployments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Edward Grefenstette, Jack Parker-Holder, Oleh Rybkin, Philip J. Ball, Stephen J. Roberts, Tim Rockt\\\"aschel, Yingchen Xu","submitted_at":"2022-10-23T12:38:03Z","abstract_excerpt":"Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate generalization, exploration should be task agnostic; 2) to facilitate scalability, exploration policies should collect large quantities of data without costly centralized retraining. Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research. We then present CASCADE, a novel approach for self-supervised exploration in this new setting. CASCADE seeks to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12719","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/2210.12719/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":"2210.12719","created_at":"2026-07-05T05:09:32.026269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12719v1","created_at":"2026-07-05T05:09:32.026269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12719","created_at":"2026-07-05T05:09:32.026269+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRDHATQSRORE","created_at":"2026-07-05T05:09:32.026269+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRDHATQSROREFI3B","created_at":"2026-07-05T05:09:32.026269+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRDHATQS","created_at":"2026-07-05T05:09:32.026269+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/TRDHATQSROREFI3BYIUSNN43KV","json":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV.json","graph_json":"https://pith.science/api/pith-number/TRDHATQSROREFI3BYIUSNN43KV/graph.json","events_json":"https://pith.science/api/pith-number/TRDHATQSROREFI3BYIUSNN43KV/events.json","paper":"https://pith.science/paper/TRDHATQS"},"agent_actions":{"view_html":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV","download_json":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV.json","view_paper":"https://pith.science/paper/TRDHATQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12719&json=true","fetch_graph":"https://pith.science/api/pith-number/TRDHATQSROREFI3BYIUSNN43KV/graph.json","fetch_events":"https://pith.science/api/pith-number/TRDHATQSROREFI3BYIUSNN43KV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/action/storage_attestation","attest_author":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/action/author_attestation","sign_citation":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/action/citation_signature","submit_replication":"https://pith.science/pith/TRDHATQSROREFI3BYIUSNN43KV/action/replication_record"}},"created_at":"2026-07-05T05:09:32.026269+00:00","updated_at":"2026-07-05T05:09:32.026269+00:00"}