{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5HSNSVZRROJJ7FHDZ4KXLIZ7J","short_pith_number":"pith:O5HSNSVZ","schema_version":"1.0","canonical_sha256":"774f26cab98c5c94fca71e78abad19fa5da88e6bc08fb6f4f05a9ed85544ca4c","source":{"kind":"arxiv","id":"2502.06301","version":2},"attestation_state":"computed","paper":{"title":"Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Maty\\'a\\v{s} Lorenc, Roman Neruda","submitted_at":"2025-02-10T09:44:10Z","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"},"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":"2502.06301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T09:44:10Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"86d71705af937110da00a702e5f0a201f2182c26e493b56feee04fbbe4712acb","abstract_canon_sha256":"b8a84b2f481af5f60dbef53fdc09a0155a9bdd3af61be440533858eecb8b3229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:27.820747Z","signature_b64":"vg4eGz04czntXSYVzWQ7+adiI42f/f3dn6mwpQGZZU7tzhhGmfUxrSaQZRALDcP+DG3jz3l0eUP69a36UWl/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"774f26cab98c5c94fca71e78abad19fa5da88e6bc08fb6f4f05a9ed85544ca4c","last_reissued_at":"2026-06-04T01:08:27.820180Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:27.820180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Maty\\'a\\v{s} Lorenc, Roman Neruda","submitted_at":"2025-02-10T09:44:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06301","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/2502.06301/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":"2502.06301","created_at":"2026-06-04T01:08:27.820248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06301v2","created_at":"2026-06-04T01:08:27.820248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06301","created_at":"2026-06-04T01:08:27.820248+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5HSNSVZRROJ","created_at":"2026-06-04T01:08:27.820248+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5HSNSVZRROJJ7FH","created_at":"2026-06-04T01:08:27.820248+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5HSNSVZ","created_at":"2026-06-04T01:08:27.820248+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/O5HSNSVZRROJJ7FHDZ4KXLIZ7J","json":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J.json","graph_json":"https://pith.science/api/pith-number/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/graph.json","events_json":"https://pith.science/api/pith-number/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/events.json","paper":"https://pith.science/paper/O5HSNSVZ"},"agent_actions":{"view_html":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J","download_json":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J.json","view_paper":"https://pith.science/paper/O5HSNSVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06301&json=true","fetch_graph":"https://pith.science/api/pith-number/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/graph.json","fetch_events":"https://pith.science/api/pith-number/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/action/storage_attestation","attest_author":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/action/author_attestation","sign_citation":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/action/citation_signature","submit_replication":"https://pith.science/pith/O5HSNSVZRROJJ7FHDZ4KXLIZ7J/action/replication_record"}},"created_at":"2026-06-04T01:08:27.820248+00:00","updated_at":"2026-06-04T01:08:27.820248+00:00"}