{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RIO7OZJ7TFNZD4SHONCQLVILE3","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":"40beb6c88113ca4b88ce67cfc535117f4779235722f01b8bacfd6dd08e84d9ae","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-08T18:55:07Z","title_canon_sha256":"87171b4334952409f02d0ebdf928c10e078ef0047df12a19b5f77b55cd44633e"},"schema_version":"1.0","source":{"id":"2101.03958","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.03958","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2101.03958v6","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03958","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"RIO7OZJ7TFNZ","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"RIO7OZJ7TFNZD4SH","created_at":"2026-07-05T05:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"RIO7OZJ7","created_at":"2026-07-05T05:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:537286ab05f83ff4566ad154475b6b58d78b645c0124e64fae18f4443d80ab9a","target":"graph","created_at":"2026-07-05T05:14:54Z","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/2101.03958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algo","authors_text":"Aleksandra Faust, Daiyi Peng, Esteban Real, Honglak Lee, John D. Co-Reyes, Quoc V. Le, Sergey Levine, Yingjie Miao","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-08T18:55:07Z","title":"Evolving Reinforcement Learning Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03958","kind":"arxiv","version":6},"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:ecc1f538662069111e381ff4ab38322d48ecf2f6089f5b438da4df01d9b505bf","target":"record","created_at":"2026-07-05T05:14:54Z","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":"40beb6c88113ca4b88ce67cfc535117f4779235722f01b8bacfd6dd08e84d9ae","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-08T18:55:07Z","title_canon_sha256":"87171b4334952409f02d0ebdf928c10e078ef0047df12a19b5f77b55cd44633e"},"schema_version":"1.0","source":{"id":"2101.03958","kind":"arxiv","version":6}},"canonical_sha256":"8a1df7653f995b91f247734505d50b26dfab710a17eeace41b5b11038fd1aff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a1df7653f995b91f247734505d50b26dfab710a17eeace41b5b11038fd1aff7","first_computed_at":"2026-07-05T05:14:54.929494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:54.929494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZpM5N7BL6vdEm0yIAgV9ZNeth8AXTfbDn/JhGZ2WyfbG/TPedyRdcvfkiiSdeqcRzQFUCVt4ATRa3blmk8yfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:54.929856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.03958","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecc1f538662069111e381ff4ab38322d48ecf2f6089f5b438da4df01d9b505bf","sha256:537286ab05f83ff4566ad154475b6b58d78b645c0124e64fae18f4443d80ab9a"],"state_sha256":"812515c9d892d9c3b8ff23ceb4be0dd64995196119b57b53763c0b2595c964b5"}