{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MLWTPH2DC6Z2KRBWLXIGSZ7NJV","short_pith_number":"pith:MLWTPH2D","schema_version":"1.0","canonical_sha256":"62ed379f4317b3a544365dd06967ed4d53500fe6b68cc4a8bc7c767453cd7c11","source":{"kind":"arxiv","id":"2312.13565","version":1},"attestation_state":"computed","paper":{"title":"Automatic Curriculum Learning with Gradient Reward Signals","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junsang Yoon, Ryan Campbell","submitted_at":"2023-12-21T04:19:43Z","abstract_excerpt":"This paper investigates the impact of using gradient norm reward signals in the context of Automatic Curriculum Learning (ACL) for deep reinforcement learning (DRL). We introduce a framework where the teacher model, utilizing the gradient norm information of a student model, dynamically adapts the learning curriculum. This approach is based on the hypothesis that gradient norms can provide a nuanced and effective measure of learning progress. Our experimental setup involves several reinforcement learning environments (PointMaze, AntMaze, and AdroitHandRelocate), to assess the efficacy of our m"},"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":"2312.13565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T04:19:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4116ff160041c6027f91c352bea2c96bf4f0f30703be13cfbb6b9bf4d981220e","abstract_canon_sha256":"b404d95d3b31691646be5efc37aeb95859ef343aec80e1140ec461593f1ae225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:46.612193Z","signature_b64":"MC40XEr2ccgARYAds5eloJqtjX06MBGTaVVQwR/YNd2e03AxATOcPV42ZtjQrmurVWbZMp2Uytbo8ytdsycZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ed379f4317b3a544365dd06967ed4d53500fe6b68cc4a8bc7c767453cd7c11","last_reissued_at":"2026-07-05T07:26:46.611748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:46.611748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Curriculum Learning with Gradient Reward Signals","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Junsang Yoon, Ryan Campbell","submitted_at":"2023-12-21T04:19:43Z","abstract_excerpt":"This paper investigates the impact of using gradient norm reward signals in the context of Automatic Curriculum Learning (ACL) for deep reinforcement learning (DRL). We introduce a framework where the teacher model, utilizing the gradient norm information of a student model, dynamically adapts the learning curriculum. This approach is based on the hypothesis that gradient norms can provide a nuanced and effective measure of learning progress. Our experimental setup involves several reinforcement learning environments (PointMaze, AntMaze, and AdroitHandRelocate), to assess the efficacy of our m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13565","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/2312.13565/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":"2312.13565","created_at":"2026-07-05T07:26:46.611807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13565v1","created_at":"2026-07-05T07:26:46.611807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13565","created_at":"2026-07-05T07:26:46.611807+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLWTPH2DC6Z2","created_at":"2026-07-05T07:26:46.611807+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLWTPH2DC6Z2KRBW","created_at":"2026-07-05T07:26:46.611807+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLWTPH2D","created_at":"2026-07-05T07:26:46.611807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02988","citing_title":"GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV","json":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV.json","graph_json":"https://pith.science/api/pith-number/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/graph.json","events_json":"https://pith.science/api/pith-number/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/events.json","paper":"https://pith.science/paper/MLWTPH2D"},"agent_actions":{"view_html":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV","download_json":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV.json","view_paper":"https://pith.science/paper/MLWTPH2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13565&json=true","fetch_graph":"https://pith.science/api/pith-number/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/graph.json","fetch_events":"https://pith.science/api/pith-number/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/action/storage_attestation","attest_author":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/action/author_attestation","sign_citation":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/action/citation_signature","submit_replication":"https://pith.science/pith/MLWTPH2DC6Z2KRBWLXIGSZ7NJV/action/replication_record"}},"created_at":"2026-07-05T07:26:46.611807+00:00","updated_at":"2026-07-05T07:26:46.611807+00:00"}