{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RV5ZVD22IJXAAP3464CJ7VEFC6","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":"e302d15b0658cee29dd7511ec2a3cd4ba84068b908bdc6c2a499900744199137","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T09:07:09Z","title_canon_sha256":"d5260aa4a899ca6da0f1aa72f6c60f61efd69e4e44fd6986fffc37d979a819ef"},"schema_version":"1.0","source":{"id":"2012.15511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15511","created_at":"2026-07-05T06:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15511v2","created_at":"2026-07-05T06:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15511","created_at":"2026-07-05T06:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"RV5ZVD22IJXA","created_at":"2026-07-05T06:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"RV5ZVD22IJXAAP34","created_at":"2026-07-05T06:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"RV5ZVD22","created_at":"2026-07-05T06:36:18Z"}],"graph_snapshots":[{"event_id":"sha256:cd3fd8256b4c2e9f5f9f2ed6e610486dd61c13920d2ae21498c4402ea7909713","target":"graph","created_at":"2026-07-05T06:36:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.15511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL. Among many asynchronous RL algorithms, arguably the most popular and effective one is the asynchronous advantage actor-critic (A3C) algorithm. Although A3C is becoming the workhorse of RL, its theoretical properties are still not well-understood, including its non-asymptotic analysis and the performance gain of parallelism (a.k.a. linear speedup). This paper revisits the A3C algorithm and establishes its non-asymptotic convergence guarantees. Unde","authors_text":"Han Shen, Kaiqing Zhang, Mingyi Hong, Tianyi Chen","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T09:07:09Z","title":"Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15511","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":"sha256:9a17a2bad03967d73fcc23749d7ccf38185977d95b9aa9f747cb282660e6e0d2","target":"record","created_at":"2026-07-05T06:36:18Z","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":"e302d15b0658cee29dd7511ec2a3cd4ba84068b908bdc6c2a499900744199137","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-31T09:07:09Z","title_canon_sha256":"d5260aa4a899ca6da0f1aa72f6c60f61efd69e4e44fd6986fffc37d979a819ef"},"schema_version":"1.0","source":{"id":"2012.15511","kind":"arxiv","version":2}},"canonical_sha256":"8d7b9a8f5a426e003f7cf7049fd48517a0f06b2340b363b0a066123bb5e175dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d7b9a8f5a426e003f7cf7049fd48517a0f06b2340b363b0a066123bb5e175dd","first_computed_at":"2026-07-05T06:36:18.766851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:18.766851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKsesLQliDNTheg8daP5QX92y8eBIeUKIovoJICmBl399HbmclNnpZgMkoCAcakE8jeFHgiKCy7Js4rL3vPvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:18.767307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a17a2bad03967d73fcc23749d7ccf38185977d95b9aa9f747cb282660e6e0d2","sha256:cd3fd8256b4c2e9f5f9f2ed6e610486dd61c13920d2ae21498c4402ea7909713"],"state_sha256":"a81c927d2d3e39e80c6cc89956b11a04be26cca28211a666510a759cb29d774f"}