{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OWK247ENSWT3G4UFVJN32RI2HB","short_pith_number":"pith:OWK247EN","schema_version":"1.0","canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","source":{"kind":"arxiv","id":"2411.01521","version":2},"attestation_state":"computed","paper":{"title":"Diversity Progress for Goal Selection in Discriminability-Motivated RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian Guckelsberger, Erik M. Lintunen, Nadia M. Ady","submitted_at":"2024-11-03T10:47:39Z","abstract_excerpt":"Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: \"Diversity Progress\" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward c"},"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":"2411.01521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"491405aca148e865a3ce3262ec1c41ef036a6db8a944edb97c340b1a5c191959","abstract_canon_sha256":"1380c5197b79c5056f7d8c066afa334a2096f98f6f7879018d85899501317009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:51.063889Z","signature_b64":"3jaLaMTA5F0rueXGoi69uRNB9BvDAK/12Ptr+4WHGDV7cZn9Kesj8eWvlqHjovBr7ignj1KViv+SnI6oKGRkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","last_reissued_at":"2026-07-05T09:31:51.063364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:51.063364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity Progress for Goal Selection in Discriminability-Motivated RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian Guckelsberger, Erik M. Lintunen, Nadia M. Ady","submitted_at":"2024-11-03T10:47:39Z","abstract_excerpt":"Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: \"Diversity Progress\" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01521","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/2411.01521/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":"2411.01521","created_at":"2026-07-05T09:31:51.063426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01521v2","created_at":"2026-07-05T09:31:51.063426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01521","created_at":"2026-07-05T09:31:51.063426+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWK247ENSWT3","created_at":"2026-07-05T09:31:51.063426+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWK247ENSWT3G4UF","created_at":"2026-07-05T09:31:51.063426+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWK247EN","created_at":"2026-07-05T09:31:51.063426+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/OWK247ENSWT3G4UFVJN32RI2HB","json":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB.json","graph_json":"https://pith.science/api/pith-number/OWK247ENSWT3G4UFVJN32RI2HB/graph.json","events_json":"https://pith.science/api/pith-number/OWK247ENSWT3G4UFVJN32RI2HB/events.json","paper":"https://pith.science/paper/OWK247EN"},"agent_actions":{"view_html":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB","download_json":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB.json","view_paper":"https://pith.science/paper/OWK247EN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01521&json=true","fetch_graph":"https://pith.science/api/pith-number/OWK247ENSWT3G4UFVJN32RI2HB/graph.json","fetch_events":"https://pith.science/api/pith-number/OWK247ENSWT3G4UFVJN32RI2HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/action/storage_attestation","attest_author":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/action/author_attestation","sign_citation":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/action/citation_signature","submit_replication":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/action/replication_record"}},"created_at":"2026-07-05T09:31:51.063426+00:00","updated_at":"2026-07-05T09:31:51.063426+00:00"}