{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VIHQXEGBT3A2CDJBFI24QNQP2U","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":"d3260cae1bf77629324da444307f867ba82b86dd4dc3f0ffee459714354e433d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-03T00:11:02Z","title_canon_sha256":"5a310f27813adaa8429173b56f5d86289efdba0adf20e0d3e8265d809f77087d"},"schema_version":"1.0","source":{"id":"2302.01470","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01470","created_at":"2026-07-05T08:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01470v3","created_at":"2026-07-05T08:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01470","created_at":"2026-07-05T08:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"VIHQXEGBT3A2","created_at":"2026-07-05T08:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"VIHQXEGBT3A2CDJB","created_at":"2026-07-05T08:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"VIHQXEGB","created_at":"2026-07-05T08:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:44dd80bf026b4aaafbe947b590ad5930389f5d6f29a2e7f201b93671e3088c85","target":"graph","created_at":"2026-07-05T08:26:56Z","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/2302.01470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learned optimizers do not work well even in simple RL tasks. We investigate this phenomenon and identify two issues. First, the agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. Moreover, due to highly stochastic agent-environment int","authors_text":"A. Rupam Mahmood, Qingfeng Lan, Shuicheng Yan, Zhongwen Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-03T00:11:02Z","title":"Learning to Optimize for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01470","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":"sha256:8fca32c5463d665f144f867d80612f91510b9ec7cd5902ef74b37c12e9df15c3","target":"record","created_at":"2026-07-05T08:26:56Z","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":"d3260cae1bf77629324da444307f867ba82b86dd4dc3f0ffee459714354e433d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-03T00:11:02Z","title_canon_sha256":"5a310f27813adaa8429173b56f5d86289efdba0adf20e0d3e8265d809f77087d"},"schema_version":"1.0","source":{"id":"2302.01470","kind":"arxiv","version":3}},"canonical_sha256":"aa0f0b90c19ec1a10d212a35c8360fd53467784bd9347833c3db9c514dc2a4a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa0f0b90c19ec1a10d212a35c8360fd53467784bd9347833c3db9c514dc2a4a3","first_computed_at":"2026-07-05T08:26:56.043096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:56.043096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RfDk/4YTRNWollDubSJDIRNGhWPs7XJdq787vMyMLW9J1akyzsUSdiXaZQKD9IcJny7baMAo4RphpT1nwsYRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:56.043562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01470","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fca32c5463d665f144f867d80612f91510b9ec7cd5902ef74b37c12e9df15c3","sha256:44dd80bf026b4aaafbe947b590ad5930389f5d6f29a2e7f201b93671e3088c85"],"state_sha256":"aee961deafa8495ac766cfc5f93c0d5a1e77ace887fa23d53aeb26aaaaf94319"}