{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HNTJVMVKDAMJS66C6KWAJNPSVV","short_pith_number":"pith:HNTJVMVK","canonical_record":{"source":{"id":"1705.07606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T08:32:10Z","cross_cats_sorted":[],"title_canon_sha256":"780f24fe3e42c128ebe0de25fda7e5117ec2891f46008da1e609f5b354e29a2e","abstract_canon_sha256":"1e9216560c3618d19a37c9e9945c405b0b4264464fa609d8a54f4ab4075e010e"},"schema_version":"1.0"},"canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","source":{"kind":"arxiv","id":"1705.07606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07606","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07606v2","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07606","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"HNTJVMVKDAMJ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HNTJVMVKDAMJS66C","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HNTJVMVK","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HNTJVMVKDAMJS66C6KWAJNPSVV","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T08:32:10Z","cross_cats_sorted":[],"title_canon_sha256":"780f24fe3e42c128ebe0de25fda7e5117ec2891f46008da1e609f5b354e29a2e","abstract_canon_sha256":"1e9216560c3618d19a37c9e9945c405b0b4264464fa609d8a54f4ab4075e010e"},"schema_version":"1.0"},"canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.330557Z","signature_b64":"vJ7LsBOe5xlOs0Wp27akek66uMCMtvA9iHebcXPT+vSzHWoal75wNS0BCoahP0YG2riERuII/C6BSczGI4pfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","last_reissued_at":"2026-05-18T00:22:49.330059Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.330059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07606","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2oux+p/vkOXdiiC5WscUR4769o8+3kEuUA43ZYs/kDuemZ/gFlH7vWa6eJcLMGexm5IpDkABCEhuk4e+2tqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:52:42.183644Z"},"content_sha256":"be973224308d4154c41ce447e371927f1a23e3d4c5d1b8a98a7da31a8926badd","schema_version":"1.0","event_id":"sha256:be973224308d4154c41ce447e371927f1a23e3d4c5d1b8a98a7da31a8926badd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HNTJVMVKDAMJS66C6KWAJNPSVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guide Actor-Critic for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Abbas Abdolmaleki, Masashi Sugiyama, Voot Tangkaratt","submitted_at":"2017-05-22T08:32:10Z","abstract_excerpt":"Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GAC). GAC firstly learns a guide actor that locally maximizes the critic and then it updates the policy parameter based on the guide actor by supervised learning. Our main theoretical contributions are two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07606","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"byCojBHHkjPR//68gJmJCaUkTzl1oRMf5u+yTMDdQxjNUnvjQg+it0PaJVE8l8ALA7MfPxR8UrCYEGPBWXxIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:52:42.183996Z"},"content_sha256":"0c5d07a401b70f0c13e42d180a1b9d6123e6718b9d47c0f153ca8997cbe7b07d","schema_version":"1.0","event_id":"sha256:0c5d07a401b70f0c13e42d180a1b9d6123e6718b9d47c0f153ca8997cbe7b07d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/bundle.json","state_url":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/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":"2026-05-28T22:52:42Z","links":{"resolver":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV","bundle":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/bundle.json","state":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HNTJVMVKDAMJS66C6KWAJNPSVV","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":"1e9216560c3618d19a37c9e9945c405b0b4264464fa609d8a54f4ab4075e010e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T08:32:10Z","title_canon_sha256":"780f24fe3e42c128ebe0de25fda7e5117ec2891f46008da1e609f5b354e29a2e"},"schema_version":"1.0","source":{"id":"1705.07606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07606","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07606v2","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07606","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"HNTJVMVKDAMJ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HNTJVMVKDAMJS66C","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HNTJVMVK","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:0c5d07a401b70f0c13e42d180a1b9d6123e6718b9d47c0f153ca8997cbe7b07d","target":"graph","created_at":"2026-05-18T00:22:49Z","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":"Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this paper, we propose a novel actor-critic method called the guide actor-critic (GAC). GAC firstly learns a guide actor that locally maximizes the critic and then it updates the policy parameter based on the guide actor by supervised learning. Our main theoretical contributions are two","authors_text":"Abbas Abdolmaleki, Masashi Sugiyama, Voot Tangkaratt","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T08:32:10Z","title":"Guide Actor-Critic for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07606","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:be973224308d4154c41ce447e371927f1a23e3d4c5d1b8a98a7da31a8926badd","target":"record","created_at":"2026-05-18T00:22:49Z","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":"1e9216560c3618d19a37c9e9945c405b0b4264464fa609d8a54f4ab4075e010e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T08:32:10Z","title_canon_sha256":"780f24fe3e42c128ebe0de25fda7e5117ec2891f46008da1e609f5b354e29a2e"},"schema_version":"1.0","source":{"id":"1705.07606","kind":"arxiv","version":2}},"canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","first_computed_at":"2026-05-18T00:22:49.330059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.330059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vJ7LsBOe5xlOs0Wp27akek66uMCMtvA9iHebcXPT+vSzHWoal75wNS0BCoahP0YG2riERuII/C6BSczGI4pfBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.330557Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be973224308d4154c41ce447e371927f1a23e3d4c5d1b8a98a7da31a8926badd","sha256:0c5d07a401b70f0c13e42d180a1b9d6123e6718b9d47c0f153ca8997cbe7b07d"],"state_sha256":"831d2bf10b54e998c322c3a5b311b7bec53376df606e58c558bfec06f836ec51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ql3cOsehdg/bGk5w8NPL5b3JvtL0+RW+sg86HuQ4GZkqWD7SzwQ4DnbkIb+RVhejgYLtPWhs/FDr590Th+QeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:52:42.186232Z","bundle_sha256":"69406d5425b13ee588cab599bb8c026dffdb10c6b281cbe7928b896009d5b107"}}