{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GWEGRSCYOEBQOWZBFGJI2H2VL2","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":"1b3b53d3ace1da000312504cee53d9b052f991853e82289ba30c0e2d2cbec258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-25T02:03:12Z","title_canon_sha256":"1bd20dd53c0f4bdb6d1eb6ca80a8132aa316b36a84fb5d7b06261e133d19475b"},"schema_version":"1.0","source":{"id":"1712.08987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.08987","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1712.08987v1","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08987","created_at":"2026-05-18T00:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"GWEGRSCYOEBQ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GWEGRSCYOEBQOWZB","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GWEGRSCY","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:3012e4272c9d551b4262c8b74f904e60117da521b6ae4a7cbc1f30b931bba894","target":"graph","created_at":"2026-05-18T00:27:08Z","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":"We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm. At inference time, our method uses a critic ensemble to select the best action from proposals of multiple actors running in parallel. By having a larger candidate set, our method can avoid actions that have fatal consequences, while staying deterministic. Using ACE, we have won the 2nd place in NIPS'17 Learning to Run competition, under the name of \"Megvii-hzwer\".","authors_text":"BoEr Zhuang, Shuchang Zhou, Xinyu Zhou, Zhewei Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-25T02:03:12Z","title":"Learning to Run with Actor-Critic Ensemble"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08987","kind":"arxiv","version":1},"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":"sha256:8ba41cca41d93ec8badd5b2eb95e8e17353553ff52eb0a509065cf6d618704d2","target":"record","created_at":"2026-05-18T00:27:08Z","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":"1b3b53d3ace1da000312504cee53d9b052f991853e82289ba30c0e2d2cbec258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-25T02:03:12Z","title_canon_sha256":"1bd20dd53c0f4bdb6d1eb6ca80a8132aa316b36a84fb5d7b06261e133d19475b"},"schema_version":"1.0","source":{"id":"1712.08987","kind":"arxiv","version":1}},"canonical_sha256":"358868c8587103075b2129928d1f555e8eb3a1a0278ab888b57384624dc38cda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"358868c8587103075b2129928d1f555e8eb3a1a0278ab888b57384624dc38cda","first_computed_at":"2026-05-18T00:27:08.796368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:08.796368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"01nOelGGckAoR89P3Nt+fYXjTG0wFRXt7J34INHfNAx+aLNkfkNkJ9z84jN7Yf364U7YSLuHnjH12ZIANEFIBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:08.797068Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.08987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ba41cca41d93ec8badd5b2eb95e8e17353553ff52eb0a509065cf6d618704d2","sha256:3012e4272c9d551b4262c8b74f904e60117da521b6ae4a7cbc1f30b931bba894"],"state_sha256":"bdab3437b362f0128e28dbd7fb96db4940b7f35835656286c5469a2d48d6e9d5"}