{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZY2BZE2PG7MWBSOR6CEDDAO6OU","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":"cb56448e6645428f6555012094abdcd1c043aaa6c0b6fcd0c419d571bccced68","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-18T07:43:00Z","title_canon_sha256":"f0226b323c17b58eb2165026d581b7e3da213c9c9b63d8624988116b6fa96fc4"},"schema_version":"1.0","source":{"id":"1809.06570","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06570","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06570v2","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06570","created_at":"2026-05-18T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZY2BZE2PG7MW","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZY2BZE2PG7MWBSOR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZY2BZE2P","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:1303c137df258a605046fd8fad0861209ee7a07ac85c6be1a943a592f8a7c397","target":"graph","created_at":"2026-05-18T00:04:39Z","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"},"paper":{"abstract_excerpt":"This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space noise. Previous methods devised a way to update the diagonal covariance matrix of a noise distribution and did not consider the direction of the noise vector and its correlation. In addition, fast updates of the noise distribution are required to facilitate policy learning. We propose a method that deforms the noise distribution according to the accumulated ","authors_text":"Izumi Karino, Kazutoshi Tanaka, Ryuma Niiyama, Yasuo Kuniyoshi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-18T07:43:00Z","title":"Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06570","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:a97b9922cbc51ff87b3c33f8e6ae4386ae7b484b3e91666345d9b2abb79b7ed2","target":"record","created_at":"2026-05-18T00:04:39Z","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":"cb56448e6645428f6555012094abdcd1c043aaa6c0b6fcd0c419d571bccced68","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-18T07:43:00Z","title_canon_sha256":"f0226b323c17b58eb2165026d581b7e3da213c9c9b63d8624988116b6fa96fc4"},"schema_version":"1.0","source":{"id":"1809.06570","kind":"arxiv","version":2}},"canonical_sha256":"ce341c934f37d960c9d1f0883181de7536effc2afb8b7ad9e7c08a85bf6f0da4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce341c934f37d960c9d1f0883181de7536effc2afb8b7ad9e7c08a85bf6f0da4","first_computed_at":"2026-05-18T00:04:39.050648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:39.050648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qbP+BWIomdUBWhi6mzRr8E0R+iXWtsmO4ZIGuEUcChXS4y6dRj3QKKZvFLkigqBEHzgOe9ZR6t5XbeR2UcRRAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:39.051197Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06570","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a97b9922cbc51ff87b3c33f8e6ae4386ae7b484b3e91666345d9b2abb79b7ed2","sha256:1303c137df258a605046fd8fad0861209ee7a07ac85c6be1a943a592f8a7c397"],"state_sha256":"cdd42cdc59d280c65e94ccba5843e10c435e4b4c40be6014678d239fa5af644b"}