{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KQBU3K7FEJGJ7G5D7GELE64K4F","short_pith_number":"pith:KQBU3K7F","schema_version":"1.0","canonical_sha256":"54034dabe5224c9f9ba3f988b27b8ae14e20409b9d2bc673575631e1e937ef09","source":{"kind":"arxiv","id":"1901.05431","version":1},"attestation_state":"computed","paper":{"title":"Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Sergent, Michael Cerny Green, Pushyami Shandilya, Vibhor Kumar","submitted_at":"2019-01-16T18:53:14Z","abstract_excerpt":"In this paper we propose a new training loop for deep reinforcement learning agents with an evolutionary generator. Evolutionary procedural content generation has been used in the creation of maps and levels for games before. Our system incorporates an evolutionary map generator to construct a training curriculum that is evolved to maximize loss within the state-of-the-art Double Dueling Deep Q Network architecture with prioritized replay. We present a case-study in which we prove the efficacy of our new method on a game with a discrete, large action space we made called Attackers and Defender"},"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":"1901.05431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-01-16T18:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"5a9deabb43b216de44cb737d0d76a2b6cfce69c29159425de5aafa4b5252a55f","abstract_canon_sha256":"03fd514745fd2d0751c2767d2d489e2d387b968dd1efd3daf053390fd3c906c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:10.891840Z","signature_b64":"4zQQIFp87rPlPlOiSE2pkFw+wlHXyhRUavANkHekscx0pZeayo8gvBCsViwSgHPwBUL8Dl5ndFFgVeMudua8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54034dabe5224c9f9ba3f988b27b8ae14e20409b9d2bc673575631e1e937ef09","last_reissued_at":"2026-05-17T23:56:10.891294Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:10.891294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Sergent, Michael Cerny Green, Pushyami Shandilya, Vibhor Kumar","submitted_at":"2019-01-16T18:53:14Z","abstract_excerpt":"In this paper we propose a new training loop for deep reinforcement learning agents with an evolutionary generator. Evolutionary procedural content generation has been used in the creation of maps and levels for games before. Our system incorporates an evolutionary map generator to construct a training curriculum that is evolved to maximize loss within the state-of-the-art Double Dueling Deep Q Network architecture with prioritized replay. We present a case-study in which we prove the efficacy of our new method on a game with a discrete, large action space we made called Attackers and Defender"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05431","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":""},"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":"1901.05431","created_at":"2026-05-17T23:56:10.891406+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.05431v1","created_at":"2026-05-17T23:56:10.891406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05431","created_at":"2026-05-17T23:56:10.891406+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQBU3K7FEJGJ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQBU3K7FEJGJ7G5D","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQBU3K7F","created_at":"2026-05-18T12:33:21.387695+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/KQBU3K7FEJGJ7G5D7GELE64K4F","json":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F.json","graph_json":"https://pith.science/api/pith-number/KQBU3K7FEJGJ7G5D7GELE64K4F/graph.json","events_json":"https://pith.science/api/pith-number/KQBU3K7FEJGJ7G5D7GELE64K4F/events.json","paper":"https://pith.science/paper/KQBU3K7F"},"agent_actions":{"view_html":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F","download_json":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F.json","view_paper":"https://pith.science/paper/KQBU3K7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.05431&json=true","fetch_graph":"https://pith.science/api/pith-number/KQBU3K7FEJGJ7G5D7GELE64K4F/graph.json","fetch_events":"https://pith.science/api/pith-number/KQBU3K7FEJGJ7G5D7GELE64K4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F/action/storage_attestation","attest_author":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F/action/author_attestation","sign_citation":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F/action/citation_signature","submit_replication":"https://pith.science/pith/KQBU3K7FEJGJ7G5D7GELE64K4F/action/replication_record"}},"created_at":"2026-05-17T23:56:10.891406+00:00","updated_at":"2026-05-17T23:56:10.891406+00:00"}