{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MSXQUDWMOVQNEQGZWPXLEIRYG2","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":"5fc63f7243604860c948018b787a35e823c920d0525fcef0e4b1b99058efb05f","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T16:29:19Z","title_canon_sha256":"c248ce8042fa515365db910057baee64b31070454bb1270b1fd5fae6f8ee74b6"},"schema_version":"1.0","source":{"id":"2007.13690","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.13690","created_at":"2026-07-05T02:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2007.13690v7","created_at":"2026-07-05T02:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13690","created_at":"2026-07-05T02:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"MSXQUDWMOVQN","created_at":"2026-07-05T02:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"MSXQUDWMOVQNEQGZ","created_at":"2026-07-05T02:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"MSXQUDWM","created_at":"2026-07-05T02:07:30Z"}],"graph_snapshots":[{"event_id":"sha256:d2f53df458ffa80635f4b1803910d393c567a06190aeca64d97bf28f6e5f8cce","target":"graph","created_at":"2026-07-05T02:07:30Z","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/2007.13690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in Reinforcement Learning (RL) have demonstrated data efficiency and optimal control over large state spaces at the cost of scalable performance. Genetic methods, on the other hand, provide scalability but depict hyperparameter sensitivity towards evolutionary operations. However, a combination of the two methods has recently demonstrated success in scaling RL agents to high-dimensional action spaces. Parallel to recent developments, we present the Evolution-based Soft Actor-Critic (ESAC), a scalable RL algorithm. We abstract exploration from exploitation by combining Evolution Strate","authors_text":"Karush Suri, Konstantinos N. Plataniotis, Xiao Qi Shi, Yuri A. Lawryshyn","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T16:29:19Z","title":"Maximum Mutation Reinforcement Learning for Scalable Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13690","kind":"arxiv","version":7},"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:f129d73b8cd5eb101003b9503b48d7fba9a2c048712379ff77ffb0ef57f7c030","target":"record","created_at":"2026-07-05T02:07:30Z","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":"5fc63f7243604860c948018b787a35e823c920d0525fcef0e4b1b99058efb05f","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-24T16:29:19Z","title_canon_sha256":"c248ce8042fa515365db910057baee64b31070454bb1270b1fd5fae6f8ee74b6"},"schema_version":"1.0","source":{"id":"2007.13690","kind":"arxiv","version":7}},"canonical_sha256":"64af0a0ecc7560d240d9b3eeb222383695d07dbdca2e748dc1c28eec858b37e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64af0a0ecc7560d240d9b3eeb222383695d07dbdca2e748dc1c28eec858b37e2","first_computed_at":"2026-07-05T02:07:30.103591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:30.103591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swxgBl9H29UsQTVevXmhtDrA6nfOnqHj+Yuu1/E+NTvxTOUVWgtwM1QgUvatiKHkGbH/j3z9uPAQ9chBYIu7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:30.104043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.13690","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f129d73b8cd5eb101003b9503b48d7fba9a2c048712379ff77ffb0ef57f7c030","sha256:d2f53df458ffa80635f4b1803910d393c567a06190aeca64d97bf28f6e5f8cce"],"state_sha256":"ea71a01b7494bce44e8cdf44a5fb9c42315bfeb72e75d9694688d9f0a26fed12"}