{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N5SOPHI4255B3HHX3DWJZZTOFZ","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":"c673864fb05ecbbceccf6ff4a1efccc565db06241e573183e792c9ac58f6fe70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-08T20:46:16Z","title_canon_sha256":"d1c34602e90bcc2897f747b1c545b0c64147d4b216863927c213b2846f57a988"},"schema_version":"1.0","source":{"id":"2204.04292","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.04292","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2204.04292v3","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04292","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"N5SOPHI4255B","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"N5SOPHI4255B3HHX","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"N5SOPHI4","created_at":"2026-07-05T06:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:32c65afb6e14beb53b29c51b6d44d0c5dfb2900493f593a24481d2ea78f1f857","target":"graph","created_at":"2026-07-05T06:03:53Z","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/2204.04292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can be a costly and painstaking process. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions. MetaPG explicitly optimizes for generalizability and performance, and implicitly optimizes the stability of both metrics. We initialize our loss function population with Soft Actor-Critic (SAC) and perform multi-objective optimization using fitness metrics encoding single-task ","authors_text":"Aaron Parisi, Aleksandra Faust, Esteban Real, Jie Tan, John D. Co-Reyes, Juan Jose Garau-Luis, Yingjie Miao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-08T20:46:16Z","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04292","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:f009dc5e1dc870d824277d3f028006d6d4504f4505319e565b05bf594fbfa53a","target":"record","created_at":"2026-07-05T06:03:53Z","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":"c673864fb05ecbbceccf6ff4a1efccc565db06241e573183e792c9ac58f6fe70","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-08T20:46:16Z","title_canon_sha256":"d1c34602e90bcc2897f747b1c545b0c64147d4b216863927c213b2846f57a988"},"schema_version":"1.0","source":{"id":"2204.04292","kind":"arxiv","version":3}},"canonical_sha256":"6f64e79d1cd77a1d9cf7d8ec9ce66e2e7ef7848eee44348c54dc48331b6ccf4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f64e79d1cd77a1d9cf7d8ec9ce66e2e7ef7848eee44348c54dc48331b6ccf4e","first_computed_at":"2026-07-05T06:03:53.888157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:53.888157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tVuKoCXSuxmu0bYrcnN1TU36J/UZqwMxJ7Yw6mmOwpg0ijWl/hQ2q/oo6AxC7HtfCmAhcTm27WjkuYfGw/pzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:53.888680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.04292","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f009dc5e1dc870d824277d3f028006d6d4504f4505319e565b05bf594fbfa53a","sha256:32c65afb6e14beb53b29c51b6d44d0c5dfb2900493f593a24481d2ea78f1f857"],"state_sha256":"0a22141f54d880f5d7c6ed064e93ec9093f8a632de7fda9da00f4ea9da001034"}