{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EKH6FJMR45Z75Z6J3GUVNQCKIN","short_pith_number":"pith:EKH6FJMR","canonical_record":{"source":{"id":"1802.07564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T13:39:28Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3084c27f34621c65f8d753e3a4163ff7647c122a14753258c3fe5fcd8e530244","abstract_canon_sha256":"9e9db5b31fb96c6ad2e688d0cfdf81d3467d020839372bec77fad01c6033f104"},"schema_version":"1.0"},"canonical_sha256":"228fe2a591e773fee7c9d9a956c04a4375f06e396c49019e0fda1071e77e4531","source":{"kind":"arxiv","id":"1802.07564","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07564","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07564v2","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07564","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"pith_short_12","alias_value":"EKH6FJMR45Z7","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EKH6FJMR45Z75Z6J","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EKH6FJMR","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EKH6FJMR45Z75Z6J3GUVNQCKIN","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T13:39:28Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3084c27f34621c65f8d753e3a4163ff7647c122a14753258c3fe5fcd8e530244","abstract_canon_sha256":"9e9db5b31fb96c6ad2e688d0cfdf81d3467d020839372bec77fad01c6033f104"},"schema_version":"1.0"},"canonical_sha256":"228fe2a591e773fee7c9d9a956c04a4375f06e396c49019e0fda1071e77e4531","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:38.238945Z","signature_b64":"rWO/N1cqWUSoOYBgk2u2sWAUyHrMJwp9Y2B30aMs/kyuiC1OaTQi+udizJtOMmS7ZnSGYYSGaNiIDoxtn8k6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"228fe2a591e773fee7c9d9a956c04a4375f06e396c49019e0fda1071e77e4531","last_reissued_at":"2026-05-18T00:12:38.238172Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:38.238172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07564","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJkh4VsXD7WV3NUWsvXJNr5h5rmPkLG55Dr39+9uUxTVlYbir1+Mn1KO0fkyLEv/vz2Gh4it/XMDgjx2HBV7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T16:41:50.171808Z"},"content_sha256":"897507aad4fdc0f357344d33335e993e5690e169a2e78c7f5298067a94745539","schema_version":"1.0","event_id":"sha256:897507aad4fdc0f357344d33335e993e5690e169a2e78c7f5298067a94745539"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EKH6FJMR45Z75Z6J3GUVNQCKIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clipped Action Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shin-ichi Maeda, Yasuhiro Fujita","submitted_at":"2018-02-21T13:39:28Z","abstract_excerpt":"Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation. We prove that our estimator, named clipped action policy gradient (CAPG), is unbiased and achieves lower variance than the conventional estimator that ignores action bounds. Experimental results demonstrate that CAPG generally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07564","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:12:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"atJ3BLDg54DUpCJWVit19jcJGqnryIvM3UipZxJJPz34/FUgTBVBhYmubdccoPHZJVqd3/Y1OmpijLEq4JGHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T16:41:50.172152Z"},"content_sha256":"db0e974cd283d43f85e0ac6e78f42f926ebab81c830312fd823de81ddaf25614","schema_version":"1.0","event_id":"sha256:db0e974cd283d43f85e0ac6e78f42f926ebab81c830312fd823de81ddaf25614"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/bundle.json","state_url":"https://pith.science/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/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":"2026-06-02T16:41:50Z","links":{"resolver":"https://pith.science/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN","bundle":"https://pith.science/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/bundle.json","state":"https://pith.science/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKH6FJMR45Z75Z6J3GUVNQCKIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EKH6FJMR45Z75Z6J3GUVNQCKIN","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":"9e9db5b31fb96c6ad2e688d0cfdf81d3467d020839372bec77fad01c6033f104","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T13:39:28Z","title_canon_sha256":"3084c27f34621c65f8d753e3a4163ff7647c122a14753258c3fe5fcd8e530244"},"schema_version":"1.0","source":{"id":"1802.07564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07564","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07564v2","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07564","created_at":"2026-05-18T00:12:38Z"},{"alias_kind":"pith_short_12","alias_value":"EKH6FJMR45Z7","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EKH6FJMR45Z75Z6J","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EKH6FJMR","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:db0e974cd283d43f85e0ac6e78f42f926ebab81c830312fd823de81ddaf25614","target":"graph","created_at":"2026-05-18T00:12:38Z","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":"Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of actions being clipped to reduce the variance in estimation. We prove that our estimator, named clipped action policy gradient (CAPG), is unbiased and achieves lower variance than the conventional estimator that ignores action bounds. Experimental results demonstrate that CAPG generally","authors_text":"Shin-ichi Maeda, Yasuhiro Fujita","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T13:39:28Z","title":"Clipped Action Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07564","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":"sha256:897507aad4fdc0f357344d33335e993e5690e169a2e78c7f5298067a94745539","target":"record","created_at":"2026-05-18T00:12:38Z","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":"9e9db5b31fb96c6ad2e688d0cfdf81d3467d020839372bec77fad01c6033f104","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-21T13:39:28Z","title_canon_sha256":"3084c27f34621c65f8d753e3a4163ff7647c122a14753258c3fe5fcd8e530244"},"schema_version":"1.0","source":{"id":"1802.07564","kind":"arxiv","version":2}},"canonical_sha256":"228fe2a591e773fee7c9d9a956c04a4375f06e396c49019e0fda1071e77e4531","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"228fe2a591e773fee7c9d9a956c04a4375f06e396c49019e0fda1071e77e4531","first_computed_at":"2026-05-18T00:12:38.238172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:38.238172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWO/N1cqWUSoOYBgk2u2sWAUyHrMJwp9Y2B30aMs/kyuiC1OaTQi+udizJtOMmS7ZnSGYYSGaNiIDoxtn8k6DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:38.238945Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:897507aad4fdc0f357344d33335e993e5690e169a2e78c7f5298067a94745539","sha256:db0e974cd283d43f85e0ac6e78f42f926ebab81c830312fd823de81ddaf25614"],"state_sha256":"e9dac9053f2832903df5fdd936152f301086c324d3055bf34a7a9e7aee031397"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sm3wLUaplVOm798cEx+qLjCG5CY5NpwyHqOrct695O55M4GRU625vTqwva33GvfQ71GsBC8clvJwRel//LhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T16:41:50.174215Z","bundle_sha256":"9480ab62b627f7a68238610d2c519af536cce741cddaaef4a6779b93af67e4a0"}}