{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DEZN4FAC2H6J3TV2VV37AX5UWF","short_pith_number":"pith:DEZN4FAC","schema_version":"1.0","canonical_sha256":"1932de1402d1fc9dcebaad77f05fb4b16f2d86cf1395745cd24fe6156cc69f6f","source":{"kind":"arxiv","id":"2003.04664","version":2},"attestation_state":"computed","paper":{"title":"Automatic Curriculum Learning For Deep RL: A Short Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Katja Hofmann, Lilian Weng, Pierre-Yves Oudeyer, R\\'emy Portelas","submitted_at":"2020-03-10T12:38:31Z","abstract_excerpt":"Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL).These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In recent years, they have been used to improve sample efficiency and asymptotic performance, to organize exploration, to encourage generalization or to solve sparse reward problems, among others. The ambition of this work is dual: 1) to present a compact and accessible introduction to the Automatic Curriculum Learning literature and 2) to draw a bigger picture of"},"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":"2003.04664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-10T12:38:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9d2273b60f9367e0186dcf4b24016c2185cf4b723af98dffe9c9a672b2df6065","abstract_canon_sha256":"06acc9c1363ad76b99c2cc527e7551ed61e9dc6383f3f576f9ff9c023a34e064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:33.381548Z","signature_b64":"bF8M72CNSYb5zXdmrOInH9sSnvXrQP/KLNaETfu85BRxdF8/JaUM9fY7N86ieD19VChhPWDbloKo+uaKysPLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1932de1402d1fc9dcebaad77f05fb4b16f2d86cf1395745cd24fe6156cc69f6f","last_reissued_at":"2026-07-05T01:06:33.381107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:33.381107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Curriculum Learning For Deep RL: A Short Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Katja Hofmann, Lilian Weng, Pierre-Yves Oudeyer, R\\'emy Portelas","submitted_at":"2020-03-10T12:38:31Z","abstract_excerpt":"Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL).These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities. In recent years, they have been used to improve sample efficiency and asymptotic performance, to organize exploration, to encourage generalization or to solve sparse reward problems, among others. The ambition of this work is dual: 1) to present a compact and accessible introduction to the Automatic Curriculum Learning literature and 2) to draw a bigger picture of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04664","kind":"arxiv","version":2},"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/2003.04664/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":"2003.04664","created_at":"2026-07-05T01:06:33.381159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.04664v2","created_at":"2026-07-05T01:06:33.381159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04664","created_at":"2026-07-05T01:06:33.381159+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEZN4FAC2H6J","created_at":"2026-07-05T01:06:33.381159+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEZN4FAC2H6J3TV2","created_at":"2026-07-05T01:06:33.381159+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEZN4FAC","created_at":"2026-07-05T01:06:33.381159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21943","citing_title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26707","citing_title":"CurEvo: Curriculum-Guided Self-Evolution for Video Understanding","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25496","citing_title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01358","citing_title":"PACE: Parameter Change for Unsupervised Environment Design","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF","json":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF.json","graph_json":"https://pith.science/api/pith-number/DEZN4FAC2H6J3TV2VV37AX5UWF/graph.json","events_json":"https://pith.science/api/pith-number/DEZN4FAC2H6J3TV2VV37AX5UWF/events.json","paper":"https://pith.science/paper/DEZN4FAC"},"agent_actions":{"view_html":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF","download_json":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF.json","view_paper":"https://pith.science/paper/DEZN4FAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.04664&json=true","fetch_graph":"https://pith.science/api/pith-number/DEZN4FAC2H6J3TV2VV37AX5UWF/graph.json","fetch_events":"https://pith.science/api/pith-number/DEZN4FAC2H6J3TV2VV37AX5UWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF/action/storage_attestation","attest_author":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF/action/author_attestation","sign_citation":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF/action/citation_signature","submit_replication":"https://pith.science/pith/DEZN4FAC2H6J3TV2VV37AX5UWF/action/replication_record"}},"created_at":"2026-07-05T01:06:33.381159+00:00","updated_at":"2026-07-05T01:06:33.381159+00:00"}