{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O5HSNSVZRROJJ7FHDZ4KXLIZ7J","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":"b8a84b2f481af5f60dbef53fdc09a0155a9bdd3af61be440533858eecb8b3229","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T09:44:10Z","title_canon_sha256":"86d71705af937110da00a702e5f0a201f2182c26e493b56feee04fbbe4712acb"},"schema_version":"1.0","source":{"id":"2502.06301","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06301","created_at":"2026-06-04T01:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06301v2","created_at":"2026-06-04T01:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06301","created_at":"2026-06-04T01:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"O5HSNSVZRROJ","created_at":"2026-06-04T01:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"O5HSNSVZRROJJ7FH","created_at":"2026-06-04T01:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"O5HSNSVZ","created_at":"2026-06-04T01:08:27Z"}],"graph_snapshots":[{"event_id":"sha256:820be94d7bc20d64d484d3c84618477eb4c1e9994a14180811d9b728e2b640c3","target":"graph","created_at":"2026-06-04T01:08:27Z","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/2502.06301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we experiment with novelty-based variants of OpenAI-ES, the NS-ES and NSR-ES algorithms, and evaluate their effectiveness in training complex, transformer-based architectures designed for the problem of reinforcement learning, such as Decision Transformers. We also test if we can accelerate the novelty-based training of these larger models by seeding the training with a pretrained models. The experimental results were mixed. NS-ES showed progress, but it would clearly need many more iterations for it to yield interesting agents. NSR-ES, on the other hand, proved quite capable of","authors_text":"Maty\\'a\\v{s} Lorenc, Roman Neruda","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T09:44:10Z","title":"Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06301","kind":"arxiv","version":2},"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":"sha256:399cb73f0531d8bb5bff7efdb65b473a06635131a3c3a30f6dba34b6b6434071","target":"record","created_at":"2026-06-04T01:08:27Z","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":"b8a84b2f481af5f60dbef53fdc09a0155a9bdd3af61be440533858eecb8b3229","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T09:44:10Z","title_canon_sha256":"86d71705af937110da00a702e5f0a201f2182c26e493b56feee04fbbe4712acb"},"schema_version":"1.0","source":{"id":"2502.06301","kind":"arxiv","version":2}},"canonical_sha256":"774f26cab98c5c94fca71e78abad19fa5da88e6bc08fb6f4f05a9ed85544ca4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"774f26cab98c5c94fca71e78abad19fa5da88e6bc08fb6f4f05a9ed85544ca4c","first_computed_at":"2026-06-04T01:08:27.820180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:27.820180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vg4eGz04czntXSYVzWQ7+adiI42f/f3dn6mwpQGZZU7tzhhGmfUxrSaQZRALDcP+DG3jz3l0eUP69a36UWl/Cg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:27.820747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06301","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:399cb73f0531d8bb5bff7efdb65b473a06635131a3c3a30f6dba34b6b6434071","sha256:820be94d7bc20d64d484d3c84618477eb4c1e9994a14180811d9b728e2b640c3"],"state_sha256":"973b28718bb4a6df9e6b41061b08f1228004cc0a476697f416d43fe975066281"}