{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HNTJVMVKDAMJS66C6KWAJNPSVV","short_pith_number":"pith:HNTJVMVK","schema_version":"1.0","canonical_sha256":"3b669ab2aa1818997bc2f2ac04b5f2ad62451bfcab7d077821bc5b15e21ad262","source":{"kind":"arxiv","id":"1705.07606","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.07606","created_at":"2026-05-18T00:22:49.330113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07606v2","created_at":"2026-05-18T00:22:49.330113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07606","created_at":"2026-05-18T00:22:49.330113+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNTJVMVKDAMJ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNTJVMVKDAMJS66C","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNTJVMVK","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV","json":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV.json","graph_json":"https://pith.science/api/pith-number/HNTJVMVKDAMJS66C6KWAJNPSVV/graph.json","events_json":"https://pith.science/api/pith-number/HNTJVMVKDAMJS66C6KWAJNPSVV/events.json","paper":"https://pith.science/paper/HNTJVMVK"},"agent_actions":{"view_html":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV","download_json":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV.json","view_paper":"https://pith.science/paper/HNTJVMVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07606&json=true","fetch_graph":"https://pith.science/api/pith-number/HNTJVMVKDAMJS66C6KWAJNPSVV/graph.json","fetch_events":"https://pith.science/api/pith-number/HNTJVMVKDAMJS66C6KWAJNPSVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/action/storage_attestation","attest_author":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/action/author_attestation","sign_citation":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/action/citation_signature","submit_replication":"https://pith.science/pith/HNTJVMVKDAMJS66C6KWAJNPSVV/action/replication_record"}},"created_at":"2026-05-18T00:22:49.330113+00:00","updated_at":"2026-05-18T00:22:49.330113+00:00"}