{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NECHJDQ3AK7YWNJV2MROT46AHB","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":"bdd4843543fb3558d1f169e5716aa2e1b29cb0d6c2a7badc6571c964b75590db","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-06T06:03:06Z","title_canon_sha256":"58f0339632035d60718cba2571be38df1f6b95af54de593f5776dcecc143e447"},"schema_version":"1.0","source":{"id":"1807.02264","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02264","created_at":"2026-05-17T23:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02264v3","created_at":"2026-05-17T23:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02264","created_at":"2026-05-17T23:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"NECHJDQ3AK7Y","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NECHJDQ3AK7YWNJV","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NECHJDQ3","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:961d41231a93c8ebc0e3e2e2c096ca15af311d00beadfac788f29829f8772848","target":"graph","created_at":"2026-05-17T23:52:33Z","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 consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on the input process, the state alone provides limited information for the expected future returns. Therefore, policy gradient methods with standard state-dependent baselines suffer high variance during training. We derive a bias-free, input-dependent baseline to reduce this varian","authors_text":"Hongzi Mao, Malte Schwarzkopf, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-06T06:03:06Z","title":"Variance Reduction for Reinforcement Learning in Input-Driven Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02264","kind":"arxiv","version":3},"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":"sha256:1df2edcf0c24d0e30203a77b8b8f7169021ee66b7a526518dde5d7da8b3f64ee","target":"record","created_at":"2026-05-17T23:52:33Z","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":"bdd4843543fb3558d1f169e5716aa2e1b29cb0d6c2a7badc6571c964b75590db","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-06T06:03:06Z","title_canon_sha256":"58f0339632035d60718cba2571be38df1f6b95af54de593f5776dcecc143e447"},"schema_version":"1.0","source":{"id":"1807.02264","kind":"arxiv","version":3}},"canonical_sha256":"6904748e1b02bf8b3535d322e9f3c0384d88a85c139e86354088c68ba3c76079","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6904748e1b02bf8b3535d322e9f3c0384d88a85c139e86354088c68ba3c76079","first_computed_at":"2026-05-17T23:52:33.934616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:33.934616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"leODgxTyU+e1eDOO7g7EA4W4aX1NyLZ6O2sl7lVua4IS7ncGks/7W19ETqP1D3yt6QVblu4km1tTRe4fFW+6AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:33.935308Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.02264","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1df2edcf0c24d0e30203a77b8b8f7169021ee66b7a526518dde5d7da8b3f64ee","sha256:961d41231a93c8ebc0e3e2e2c096ca15af311d00beadfac788f29829f8772848"],"state_sha256":"053028d2049d7ac9e3e43984bc80db8ecac67364cbf173a529e97cb2e69e11bc"}