{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VQ5R7CU5VJNUTAHKGGECEBEABF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8886a3bdef05449d972dbb27336e05750bf1d1199f9a6b4d7ce24053702de5c9","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T14:16:13Z","title_canon_sha256":"3841d6e7c6f34bf9d7410cf069c1ad774623306ec43f7892341f1d52a3fdac0b"},"schema_version":"1.0","source":{"id":"2101.09721","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09721","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09721v3","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09721","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_12","alias_value":"VQ5R7CU5VJNU","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_16","alias_value":"VQ5R7CU5VJNUTAHK","created_at":"2026-07-05T02:13:22Z"},{"alias_kind":"pith_short_8","alias_value":"VQ5R7CU5","created_at":"2026-07-05T02:13:22Z"}],"graph_snapshots":[{"event_id":"sha256:6fad03b8404a6eea81ce018e60d8bf064586713fd909c93eaaddd1d532b1dcf3","target":"graph","created_at":"2026-07-05T02:13:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.09721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fabio Ferreira, Frank Hutter, Thomas Nierhoff","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T14:16:13Z","title":"Learning Synthetic Environments for Reinforcement Learning with Evolution Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09721","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:142b4f04f35324a14580a530212dc2253ad0f235cfddf91a9dca181ab18da5cc","target":"record","created_at":"2026-07-05T02:13:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8886a3bdef05449d972dbb27336e05750bf1d1199f9a6b4d7ce24053702de5c9","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T14:16:13Z","title_canon_sha256":"3841d6e7c6f34bf9d7410cf069c1ad774623306ec43f7892341f1d52a3fdac0b"},"schema_version":"1.0","source":{"id":"2101.09721","kind":"arxiv","version":3}},"canonical_sha256":"ac3b1f8a9daa5b4980ea31882204800973c92db390232d92dd26666f1a8525ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac3b1f8a9daa5b4980ea31882204800973c92db390232d92dd26666f1a8525ae","first_computed_at":"2026-07-05T02:13:22.047290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:22.047290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wQnDQOlGom/KONw/KIrJajoI9Ck7SP5U8I0wstgme9PAM4LWEcWtB5fn6k5eDeF9FQyw1zbE+pPwf5br0BxdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:22.047724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09721","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:142b4f04f35324a14580a530212dc2253ad0f235cfddf91a9dca181ab18da5cc","sha256:6fad03b8404a6eea81ce018e60d8bf064586713fd909c93eaaddd1d532b1dcf3"],"state_sha256":"3e7fc9a3befd721406a17d6eb3c8e6bc34698a66e5bd7c31aec36e46017a3396"}