{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CFKWL3VQ3H3ZGKQOC5Y7RJWFAR","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":"aa8b7e1f260a543e4563ddfa839acd5d870d6cf43023f4c297b6a8694ae70daf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2022-04-07T17:26:58Z","title_canon_sha256":"adbf0e19e7778cc9fc8ea609ea21e56d15265f9f2f0a0f099ca2a9ba15449c50"},"schema_version":"1.0","source":{"id":"2204.03656","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03656","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03656v2","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03656","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"CFKWL3VQ3H3Z","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"CFKWL3VQ3H3ZGKQO","created_at":"2026-07-05T05:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"CFKWL3VQ","created_at":"2026-07-05T05:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:be5a4e72e5f473dd49da16d928d608e17a2bb9d12c531f4992b8a8ec8a39c104","target":"graph","created_at":"2026-07-05T05:12:28Z","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/2204.03656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning agents can make use of Reinforcement Learning (RL) to decide their actions by using a reward function. However, the learning process is greatly influenced by the elect of values of the hyperparameters used in the learning algorithm. This work proposed a Deep Deterministic Policy Gradient (DDPG) and Hindsight Experience Replay (HER) based method, which makes use of the Genetic Algorithm (GA) to fine-tune the hyperparameters' values. This method (GA+DDPG+HER) experimented on six robotic manipulation tasks: FetchReach; FetchSlide; FetchPush; FetchPickAndPlace; DoorOpening; and AuboReach.","authors_text":"Adarsh Sehgal, Hung La, Nicholas Ward, Sushil Louis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2022-04-07T17:26:58Z","title":"Automatic Parameter Optimization Using Genetic Algorithm in Deep Reinforcement Learning for Robotic Manipulation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03656","kind":"arxiv","version":2},"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":"sha256:10f1e68621a92c5e1cd89caafa158164443e1f984f218b028446b01c1adbbd09","target":"record","created_at":"2026-07-05T05:12:28Z","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":"aa8b7e1f260a543e4563ddfa839acd5d870d6cf43023f4c297b6a8694ae70daf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2022-04-07T17:26:58Z","title_canon_sha256":"adbf0e19e7778cc9fc8ea609ea21e56d15265f9f2f0a0f099ca2a9ba15449c50"},"schema_version":"1.0","source":{"id":"2204.03656","kind":"arxiv","version":2}},"canonical_sha256":"115565eeb0d9f7932a0e1771f8a6c504438a2388dea7bcbe7b0598d4530d1531","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"115565eeb0d9f7932a0e1771f8a6c504438a2388dea7bcbe7b0598d4530d1531","first_computed_at":"2026-07-05T05:12:28.347949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:28.347949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lKxqsJDPqfR8ueDyazSHSGdQ169cNZ/+7cU0L+2Mrrvra8llClhPaVJJMfFa5xoqEz9spP56S4hOkB8Idzl+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:28.348481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03656","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10f1e68621a92c5e1cd89caafa158164443e1f984f218b028446b01c1adbbd09","sha256:be5a4e72e5f473dd49da16d928d608e17a2bb9d12c531f4992b8a8ec8a39c104"],"state_sha256":"40384fc218f35d93f4dc4a36bc0ade920903960dfda002949a9953bd93504386"}