{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6FWIAGOGUH7LI6GNQGHRFRWB5O","short_pith_number":"pith:6FWIAGOG","schema_version":"1.0","canonical_sha256":"f16c8019c6a1feb478cd818f12c6c1ebafc85f6853b56b402f5eb27da193efec","source":{"kind":"arxiv","id":"2010.03934","version":4},"attestation_state":"computed","paper":{"title":"Prioritized Level Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edward Grefenstette, Minqi Jiang, Tim Rockt\\\"aschel","submitted_at":"2020-10-08T12:46:57Z","abstract_excerpt":"Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a unique configuration of its factors of variation. Training on a prespecified subset of levels allows for testing generalization to unseen levels. What can be learned from a level depends on the current policy, yet prior work defaults to uniform sampling of training levels independently of the policy. We introduce Prioritized Level Replay (PLR), a general framewor"},"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":"2010.03934","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T12:46:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a47e60ff846bea19286f8303da79cfbbac104a3237d8e28076af4cc5ccba90b","abstract_canon_sha256":"36cf286fb865b3efdbc5d7b45eaf5a4f8eee05c0a829c0f55b8027436a2749a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:34.264469Z","signature_b64":"pfEL5G29lCFx3wbGXY0LwhUZcn8tPYyMYwtDYnQgiHkC2VCuamWW3ZNhIPJw244r43YnL3D5jPFZlhYqiYtCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16c8019c6a1feb478cd818f12c6c1ebafc85f6853b56b402f5eb27da193efec","last_reissued_at":"2026-07-05T02:48:34.264040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:34.264040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prioritized Level Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Edward Grefenstette, Minqi Jiang, Tim Rockt\\\"aschel","submitted_at":"2020-10-08T12:46:57Z","abstract_excerpt":"Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning. In this setting, each level is an algorithmically created environment instance with a unique configuration of its factors of variation. Training on a prespecified subset of levels allows for testing generalization to unseen levels. What can be learned from a level depends on the current policy, yet prior work defaults to uniform sampling of training levels independently of the policy. We introduce Prioritized Level Replay (PLR), a general framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03934","kind":"arxiv","version":4},"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/2010.03934/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":"2010.03934","created_at":"2026-07-05T02:48:34.264102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03934v4","created_at":"2026-07-05T02:48:34.264102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03934","created_at":"2026-07-05T02:48:34.264102+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FWIAGOGUH7L","created_at":"2026-07-05T02:48:34.264102+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FWIAGOGUH7LI6GN","created_at":"2026-07-05T02:48:34.264102+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FWIAGOG","created_at":"2026-07-05T02:48:34.264102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27348","citing_title":"Bridging Performance and Generalization in Reinforcement Learning for Agile Flight","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03800","citing_title":"Trading Human Curation for Synthetic Augmentation in RLVR","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O","json":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O.json","graph_json":"https://pith.science/api/pith-number/6FWIAGOGUH7LI6GNQGHRFRWB5O/graph.json","events_json":"https://pith.science/api/pith-number/6FWIAGOGUH7LI6GNQGHRFRWB5O/events.json","paper":"https://pith.science/paper/6FWIAGOG"},"agent_actions":{"view_html":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O","download_json":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O.json","view_paper":"https://pith.science/paper/6FWIAGOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03934&json=true","fetch_graph":"https://pith.science/api/pith-number/6FWIAGOGUH7LI6GNQGHRFRWB5O/graph.json","fetch_events":"https://pith.science/api/pith-number/6FWIAGOGUH7LI6GNQGHRFRWB5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O/action/storage_attestation","attest_author":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O/action/author_attestation","sign_citation":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O/action/citation_signature","submit_replication":"https://pith.science/pith/6FWIAGOGUH7LI6GNQGHRFRWB5O/action/replication_record"}},"created_at":"2026-07-05T02:48:34.264102+00:00","updated_at":"2026-07-05T02:48:34.264102+00:00"}