{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z4HJLV4KIDQPXR7HVONY57ZEW2","short_pith_number":"pith:Z4HJLV4K","canonical_record":{"source":{"id":"2201.04286","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-12T03:31:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8db946efaf94c34a7b9d6ac43715ca3266264fb3a6bc778c311712427238d422","abstract_canon_sha256":"9eaf738c3b160622197764af564d3d40cec902d74eb8c0ff062370fde67d2c32"},"schema_version":"1.0"},"canonical_sha256":"cf0e95d78a40e0fbc7e7ab9b8eff24b6a217fb22bc4c3253925b23f1063a1a80","source":{"kind":"arxiv","id":"2201.04286","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04286","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04286v4","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04286","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z4HJLV4KIDQP","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z4HJLV4KIDQPXR7H","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z4HJLV4K","created_at":"2026-07-05T04:58:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z4HJLV4KIDQPXR7HVONY57ZEW2","target":"record","payload":{"canonical_record":{"source":{"id":"2201.04286","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-12T03:31:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8db946efaf94c34a7b9d6ac43715ca3266264fb3a6bc778c311712427238d422","abstract_canon_sha256":"9eaf738c3b160622197764af564d3d40cec902d74eb8c0ff062370fde67d2c32"},"schema_version":"1.0"},"canonical_sha256":"cf0e95d78a40e0fbc7e7ab9b8eff24b6a217fb22bc4c3253925b23f1063a1a80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:02.421631Z","signature_b64":"ta2FBRISyyM+SgXUntGe0D31tRixlnD6M0Ws7bl04VSvj3s6UiG0pp/6QD+GLVywFdbzEp5KvYE7EAnzSXARCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf0e95d78a40e0fbc7e7ab9b8eff24b6a217fb22bc4c3253925b23f1063a1a80","last_reissued_at":"2026-07-05T04:58:02.421171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:02.421171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.04286","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ULoz2xF4MFiDIJpcvPDPeSYi+WEnKLCxLHnJYFtbwBXE2xyRvHcZePuiM7/RtrU56FDrcVodmTMyx8kT7d8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:04:57.120028Z"},"content_sha256":"598eb2a9b2376bc2ea61c52a75b5bd7dafae7bdf84163ea60845b23624fca943","schema_version":"1.0","event_id":"sha256:598eb2a9b2376bc2ea61c52a75b5bd7dafae7bdf84163ea60845b23624fca943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z4HJLV4KIDQPXR7HVONY57ZEW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evolutionary Action Selection for Gradient-based Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Bingsheng Wei, Kang Xu, Tianxing Liu, Wei Li, Yan Ma, Yi Liu","submitted_at":"2022-01-12T03:31:21Z","abstract_excerpt":"Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid methods maintains a population of policy networks.However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA.In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space.We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04286","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.04286/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOHh0t9kdDCL94QXPMjcYYt4n+9F+0HBxW+FwXucF1f8e5eem/rWu3ULmnhBNH+m/YIuHpcBcbjdPTbFe8m4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:04:57.120914Z"},"content_sha256":"9535b0cb2acf37d0c8b6beb290c6ec499ec521058cde836f30c0eeacdb86c787","schema_version":"1.0","event_id":"sha256:9535b0cb2acf37d0c8b6beb290c6ec499ec521058cde836f30c0eeacdb86c787"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/bundle.json","state_url":"https://pith.science/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T18:04:57Z","links":{"resolver":"https://pith.science/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2","bundle":"https://pith.science/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/bundle.json","state":"https://pith.science/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4HJLV4KIDQPXR7HVONY57ZEW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z4HJLV4KIDQPXR7HVONY57ZEW2","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":"9eaf738c3b160622197764af564d3d40cec902d74eb8c0ff062370fde67d2c32","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-12T03:31:21Z","title_canon_sha256":"8db946efaf94c34a7b9d6ac43715ca3266264fb3a6bc778c311712427238d422"},"schema_version":"1.0","source":{"id":"2201.04286","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04286","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04286v4","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04286","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z4HJLV4KIDQP","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z4HJLV4KIDQPXR7H","created_at":"2026-07-05T04:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z4HJLV4K","created_at":"2026-07-05T04:58:02Z"}],"graph_snapshots":[{"event_id":"sha256:9535b0cb2acf37d0c8b6beb290c6ec499ec521058cde836f30c0eeacdb86c787","target":"graph","created_at":"2026-07-05T04:58:02Z","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/2201.04286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid methods maintains a population of policy networks.However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA.In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space.We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gr","authors_text":"Bingsheng Wei, Kang Xu, Tianxing Liu, Wei Li, Yan Ma, Yi Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-12T03:31:21Z","title":"Evolutionary Action Selection for Gradient-based Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04286","kind":"arxiv","version":4},"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":"sha256:598eb2a9b2376bc2ea61c52a75b5bd7dafae7bdf84163ea60845b23624fca943","target":"record","created_at":"2026-07-05T04:58:02Z","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":"9eaf738c3b160622197764af564d3d40cec902d74eb8c0ff062370fde67d2c32","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-01-12T03:31:21Z","title_canon_sha256":"8db946efaf94c34a7b9d6ac43715ca3266264fb3a6bc778c311712427238d422"},"schema_version":"1.0","source":{"id":"2201.04286","kind":"arxiv","version":4}},"canonical_sha256":"cf0e95d78a40e0fbc7e7ab9b8eff24b6a217fb22bc4c3253925b23f1063a1a80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf0e95d78a40e0fbc7e7ab9b8eff24b6a217fb22bc4c3253925b23f1063a1a80","first_computed_at":"2026-07-05T04:58:02.421171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:02.421171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ta2FBRISyyM+SgXUntGe0D31tRixlnD6M0Ws7bl04VSvj3s6UiG0pp/6QD+GLVywFdbzEp5KvYE7EAnzSXARCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:02.421631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04286","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:598eb2a9b2376bc2ea61c52a75b5bd7dafae7bdf84163ea60845b23624fca943","sha256:9535b0cb2acf37d0c8b6beb290c6ec499ec521058cde836f30c0eeacdb86c787"],"state_sha256":"3ab8b76159024af6bfa4b860612d3d27856f02cebbcfd4dadc4cd1d6e638fc39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ulMMuU6++0icm3ub0cUQvw0d3WE3XPubb2bmkZ6kTXwcMWZcvTqbGLlH/m33Kdr5wPeaSIozYobgIum+zk4NAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:04:57.127277Z","bundle_sha256":"e44dac6034d13b9cefebcff330611c3ceb6e51142e9951ea5c1887693c48b23d"}}