{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RLUGOAK23OTBBSJM4SFBDHLK7F","short_pith_number":"pith:RLUGOAK2","canonical_record":{"source":{"id":"1811.02696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T22:32:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e51bd6a829cc5feb91716e8cab6be2b281400830bd2606af706f89de92b002cf","abstract_canon_sha256":"39f82655af2c83a618500cc52db6c4c5c2e6d342191187163098e0cfd0e79eae"},"schema_version":"1.0"},"canonical_sha256":"8ae867015adba610c92ce48a119d6af95594a0d18f10bd5095db6af4ede7ec4f","source":{"kind":"arxiv","id":"1811.02696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02696","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02696v1","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02696","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"RLUGOAK23OTB","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RLUGOAK23OTBBSJM","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RLUGOAK2","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RLUGOAK23OTBBSJM4SFBDHLK7F","target":"record","payload":{"canonical_record":{"source":{"id":"1811.02696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T22:32:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e51bd6a829cc5feb91716e8cab6be2b281400830bd2606af706f89de92b002cf","abstract_canon_sha256":"39f82655af2c83a618500cc52db6c4c5c2e6d342191187163098e0cfd0e79eae"},"schema_version":"1.0"},"canonical_sha256":"8ae867015adba610c92ce48a119d6af95594a0d18f10bd5095db6af4ede7ec4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:14.436068Z","signature_b64":"0zIiV8s8J2sVnb9EUMZUHz5MgxZvmmwgmvVuCu4pUj0w6de42liEcIRS2jNbJfOJcHUKOMiZQUTjYRljkjjZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae867015adba610c92ce48a119d6af95594a0d18f10bd5095db6af4ede7ec4f","last_reissued_at":"2026-05-18T00:01:14.435606Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:14.435606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.02696","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I2/kU5HOHjCgWOEoWUJRax1J9lTpZYy84JKZzmHsoKy6/JorfWpQuTyu8B8eVjIqa1PDBI00sTc4AbgyXbriBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:04:51.661044Z"},"content_sha256":"975669ced815703b9407d2db292c4cf4675921f1594f3b0cf1f4668e9d05e061","schema_version":"1.0","event_id":"sha256:975669ced815703b9407d2db292c4cf4675921f1594f3b0cf1f4668e9d05e061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RLUGOAK23OTBBSJM4SFBDHLK7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Hengshuai Yao, Shangtong Zhang","submitted_at":"2018-11-06T22:32:55Z","abstract_excerpt":"In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic. Besides the ensemble perspective, we also formulate ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options. Furthermore, we perform a look-ahead tree search with those actors and a learned value prediction model, resulting in a refined value esti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02696","kind":"arxiv","version":1},"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":"2026-05-18T00:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QUR/2WMmOOyrwaJsMQ00ivfcfbsi8ybgxd2aRY2D6zT2DiHhyBKWU9uC/kq76S9sNHvKcTP7v0GfdyJTghc/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T02:04:51.661397Z"},"content_sha256":"3199c0d34b24e9e5c8b55f3dcd4e5d6b13f31c3931cf7dcc7fcef01141c818c0","schema_version":"1.0","event_id":"sha256:3199c0d34b24e9e5c8b55f3dcd4e5d6b13f31c3931cf7dcc7fcef01141c818c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/bundle.json","state_url":"https://pith.science/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/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":"2026-06-07T02:04:51Z","links":{"resolver":"https://pith.science/pith/RLUGOAK23OTBBSJM4SFBDHLK7F","bundle":"https://pith.science/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/bundle.json","state":"https://pith.science/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLUGOAK23OTBBSJM4SFBDHLK7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RLUGOAK23OTBBSJM4SFBDHLK7F","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":"39f82655af2c83a618500cc52db6c4c5c2e6d342191187163098e0cfd0e79eae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T22:32:55Z","title_canon_sha256":"e51bd6a829cc5feb91716e8cab6be2b281400830bd2606af706f89de92b002cf"},"schema_version":"1.0","source":{"id":"1811.02696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02696","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02696v1","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02696","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"RLUGOAK23OTB","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RLUGOAK23OTBBSJM","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RLUGOAK2","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:3199c0d34b24e9e5c8b55f3dcd4e5d6b13f31c3931cf7dcc7fcef01141c818c0","target":"graph","created_at":"2026-05-18T00:01:14Z","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":"In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic. Besides the ensemble perspective, we also formulate ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options. Furthermore, we perform a look-ahead tree search with those actors and a learned value prediction model, resulting in a refined value esti","authors_text":"Hao Chen, Hengshuai Yao, Shangtong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T22:32:55Z","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02696","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":"sha256:975669ced815703b9407d2db292c4cf4675921f1594f3b0cf1f4668e9d05e061","target":"record","created_at":"2026-05-18T00:01:14Z","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":"39f82655af2c83a618500cc52db6c4c5c2e6d342191187163098e0cfd0e79eae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-06T22:32:55Z","title_canon_sha256":"e51bd6a829cc5feb91716e8cab6be2b281400830bd2606af706f89de92b002cf"},"schema_version":"1.0","source":{"id":"1811.02696","kind":"arxiv","version":1}},"canonical_sha256":"8ae867015adba610c92ce48a119d6af95594a0d18f10bd5095db6af4ede7ec4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ae867015adba610c92ce48a119d6af95594a0d18f10bd5095db6af4ede7ec4f","first_computed_at":"2026-05-18T00:01:14.435606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:14.435606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zIiV8s8J2sVnb9EUMZUHz5MgxZvmmwgmvVuCu4pUj0w6de42liEcIRS2jNbJfOJcHUKOMiZQUTjYRljkjjZDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:14.436068Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:975669ced815703b9407d2db292c4cf4675921f1594f3b0cf1f4668e9d05e061","sha256:3199c0d34b24e9e5c8b55f3dcd4e5d6b13f31c3931cf7dcc7fcef01141c818c0"],"state_sha256":"11238a022f51dce79e41cd19665478cd47e8440fe73b2f4d06b21fe19a9ce761"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17BG1h55bjaLvHJ+bgb4RVy7yYrbGkcv6IJDzI3XNtYyiySZKMhEVHguRl4RZi26Dr9YPwywoVuDpuSl6vepBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T02:04:51.663228Z","bundle_sha256":"7465bca862be10fb150efafacc4a78982a72a92b569df2dc808b2e7e9af8e21a"}}