{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VQ5R7CU5VJNUTAHKGGECEBEABF","short_pith_number":"pith:VQ5R7CU5","schema_version":"1.0","canonical_sha256":"ac3b1f8a9daa5b4980ea31882204800973c92db390232d92dd26666f1a8525ae","source":{"kind":"arxiv","id":"2101.09721","version":3},"attestation_state":"computed","paper":{"title":"Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Fabio Ferreira, Frank Hutter, Thomas Nierhoff","submitted_at":"2021-01-24T14:16:13Z","abstract_excerpt":"This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target environment. We formulate this as a bi-level optimization problem and represent an SE as a neural network. By using Natural Evolution Strategies and a population of SE parameter vectors, we train agents in the inner loop on evolving SEs while in the outer loop we use the performance on the target task as a score for meta-updating the SE population. We show empirical"},"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":"2101.09721","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T14:16:13Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"3841d6e7c6f34bf9d7410cf069c1ad774623306ec43f7892341f1d52a3fdac0b","abstract_canon_sha256":"8886a3bdef05449d972dbb27336e05750bf1d1199f9a6b4d7ce24053702de5c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:22.047724Z","signature_b64":"wQnDQOlGom/KONw/KIrJajoI9Ck7SP5U8I0wstgme9PAM4LWEcWtB5fn6k5eDeF9FQyw1zbE+pPwf5br0BxdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac3b1f8a9daa5b4980ea31882204800973c92db390232d92dd26666f1a8525ae","last_reissued_at":"2026-07-05T02:13:22.047290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:22.047290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Fabio Ferreira, Frank Hutter, Thomas Nierhoff","submitted_at":"2021-01-24T14:16:13Z","abstract_excerpt":"This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target environment. We formulate this as a bi-level optimization problem and represent an SE as a neural network. By using Natural Evolution Strategies and a population of SE parameter vectors, we train agents in the inner loop on evolving SEs while in the outer loop we use the performance on the target task as a score for meta-updating the SE population. We show empirical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09721","kind":"arxiv","version":3},"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/2101.09721/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":"2101.09721","created_at":"2026-07-05T02:13:22.047350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09721v3","created_at":"2026-07-05T02:13:22.047350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09721","created_at":"2026-07-05T02:13:22.047350+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ5R7CU5VJNU","created_at":"2026-07-05T02:13:22.047350+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ5R7CU5VJNUTAHK","created_at":"2026-07-05T02:13:22.047350+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ5R7CU5","created_at":"2026-07-05T02:13:22.047350+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/VQ5R7CU5VJNUTAHKGGECEBEABF","json":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF.json","graph_json":"https://pith.science/api/pith-number/VQ5R7CU5VJNUTAHKGGECEBEABF/graph.json","events_json":"https://pith.science/api/pith-number/VQ5R7CU5VJNUTAHKGGECEBEABF/events.json","paper":"https://pith.science/paper/VQ5R7CU5"},"agent_actions":{"view_html":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF","download_json":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF.json","view_paper":"https://pith.science/paper/VQ5R7CU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09721&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ5R7CU5VJNUTAHKGGECEBEABF/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ5R7CU5VJNUTAHKGGECEBEABF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF/action/storage_attestation","attest_author":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF/action/author_attestation","sign_citation":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF/action/citation_signature","submit_replication":"https://pith.science/pith/VQ5R7CU5VJNUTAHKGGECEBEABF/action/replication_record"}},"created_at":"2026-07-05T02:13:22.047350+00:00","updated_at":"2026-07-05T02:13:22.047350+00:00"}