{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:L4AG4CKL4LPVI2TDXB3L6GK4NK","short_pith_number":"pith:L4AG4CKL","canonical_record":{"source":{"id":"2005.03557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15f4283f5e2e0ee0d88d343185085d04e4a6c0def1ce49ea284094fd14687c5f","abstract_canon_sha256":"942db39dde827a9c4ed96c707c7b7f8b8fb989f68d13935e93bd93fc1d373a76"},"schema_version":"1.0"},"canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","source":{"kind":"arxiv","id":"2005.03557","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03557","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03557v2","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03557","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"L4AG4CKL4LPV","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"L4AG4CKL4LPVI2TD","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"L4AG4CKL","created_at":"2026-07-05T01:01:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:L4AG4CKL4LPVI2TDXB3L6GK4NK","target":"record","payload":{"canonical_record":{"source":{"id":"2005.03557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15f4283f5e2e0ee0d88d343185085d04e4a6c0def1ce49ea284094fd14687c5f","abstract_canon_sha256":"942db39dde827a9c4ed96c707c7b7f8b8fb989f68d13935e93bd93fc1d373a76"},"schema_version":"1.0"},"canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:25.095364Z","signature_b64":"OElURGLtUnno3LUpaI9kWV9aedpd8Gxa1eO3Y4C2XWHGE9eFNDS5bg3ED1fi3tLilLbPxBkdKEFy29hq7y9rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","last_reissued_at":"2026-07-05T01:01:25.095013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:25.095013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.03557","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":"2026-07-05T01:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x0Om4a8OUb3koUHF9LS2y8ApFXx7YjcFw1yevrA9P4Ep2ayjtpZ1lcDDrElEVlVcc1wvkHn+3y3TFIJxEqM9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:46:43.166184Z"},"content_sha256":"0d0f645b9709e6aa8746057111719eaf78f23e463c56c3e95e249af62ac6c4eb","schema_version":"1.0","event_id":"sha256:0d0f645b9709e6aa8746057111719eaf78f23e463c56c3e95e249af62ac6c4eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:L4AG4CKL4LPVI2TDXB3L6GK4NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tengyu Xu, Yingbin Liang, Zhe Wang","submitted_at":"2020-05-07T15:42:31Z","abstract_excerpt":"As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established. The second two time-scale design, in which actor and critic update simultaneously but with different learning rates, has much fewer tuning parameters than the nested-loop design and is he"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03557","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.03557/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+smIKTCOonyQV/TbrBBLoYCgFDSXKSaTWPb2DtO2S8gqOOwHUP8L84//FdY+/0SKJhMRpxR1j+496jvr99kCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T14:46:43.167146Z"},"content_sha256":"8de19330559635ca3d7d603c9c977ec3ae2a6e0a88dabed88623acf7abbe4ce2","schema_version":"1.0","event_id":"sha256:8de19330559635ca3d7d603c9c977ec3ae2a6e0a88dabed88623acf7abbe4ce2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/bundle.json","state_url":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/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":"2026-08-16T14:46:43Z","links":{"resolver":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK","bundle":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/bundle.json","state":"https://pith.science/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4AG4CKL4LPVI2TDXB3L6GK4NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:L4AG4CKL4LPVI2TDXB3L6GK4NK","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":"942db39dde827a9c4ed96c707c7b7f8b8fb989f68d13935e93bd93fc1d373a76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","title_canon_sha256":"15f4283f5e2e0ee0d88d343185085d04e4a6c0def1ce49ea284094fd14687c5f"},"schema_version":"1.0","source":{"id":"2005.03557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03557","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03557v2","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03557","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"L4AG4CKL4LPV","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_16","alias_value":"L4AG4CKL4LPVI2TD","created_at":"2026-07-05T01:01:25Z"},{"alias_kind":"pith_short_8","alias_value":"L4AG4CKL","created_at":"2026-07-05T01:01:25Z"}],"graph_snapshots":[{"event_id":"sha256:8de19330559635ca3d7d603c9c977ec3ae2a6e0a88dabed88623acf7abbe4ce2","target":"graph","created_at":"2026-07-05T01:01:25Z","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/2005.03557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established. The second two time-scale design, in which actor and critic update simultaneously but with different learning rates, has much fewer tuning parameters than the nested-loop design and is he","authors_text":"Tengyu Xu, Yingbin Liang, Zhe Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","title":"Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03557","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":"sha256:0d0f645b9709e6aa8746057111719eaf78f23e463c56c3e95e249af62ac6c4eb","target":"record","created_at":"2026-07-05T01:01:25Z","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":"942db39dde827a9c4ed96c707c7b7f8b8fb989f68d13935e93bd93fc1d373a76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T15:42:31Z","title_canon_sha256":"15f4283f5e2e0ee0d88d343185085d04e4a6c0def1ce49ea284094fd14687c5f"},"schema_version":"1.0","source":{"id":"2005.03557","kind":"arxiv","version":2}},"canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f006e094be2df546a63b876bf195c6a95945169f7d6d21dee29cba2d660038c","first_computed_at":"2026-07-05T01:01:25.095013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:25.095013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OElURGLtUnno3LUpaI9kWV9aedpd8Gxa1eO3Y4C2XWHGE9eFNDS5bg3ED1fi3tLilLbPxBkdKEFy29hq7y9rCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:25.095364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.03557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d0f645b9709e6aa8746057111719eaf78f23e463c56c3e95e249af62ac6c4eb","sha256:8de19330559635ca3d7d603c9c977ec3ae2a6e0a88dabed88623acf7abbe4ce2"],"state_sha256":"fb3d63057217888ab13b639fa5eca93b7d8cbaaa8980ee08054ba41bdf9ba031"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2uKnpLhecin4mnv/CBakd78g5PUe6Tkg6g7sBJE6qTeBXtPTIbqUnuWY9SW6iRmZwxYO+SpPniJt+ycgdkADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T14:46:43.175726Z","bundle_sha256":"7776c55e1d8da4332f70cae7707bf2237f3255ae66d46051d64aa702e5a9bcd7"}}