{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CLWWXMVTFRKXOAAW5AXDL5K7XS","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":"547f6c00f4bc96be7d9bad78698966495b93a6c9d84bfecfbbdf983a0eec9bfb","cross_cats_sorted":["cs.CC","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T05:03:19Z","title_canon_sha256":"e97062a624e05db64f958f3f5b3f45c9993fbd39c68727ea044d0258c7647c1d"},"schema_version":"1.0","source":{"id":"1710.06100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06100","created_at":"2026-05-18T00:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06100v1","created_at":"2026-05-18T00:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06100","created_at":"2026-05-18T00:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"CLWWXMVTFRKX","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CLWWXMVTFRKXOAAW","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CLWWXMVT","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:8dca70c3e71fb4de7031e7a7b136e4ccc1f3c5684202771cad19f3379e902616","target":"graph","created_at":"2026-05-18T00:32:37Z","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":"Consider the problem of approximating the optimal policy of a Markov decision process (MDP) by sampling state transitions. In contrast to existing reinforcement learning methods that are based on successive approximations to the nonlinear Bellman equation, we propose a Primal-Dual $\\pi$ Learning method in light of the linear duality between the value and policy. The $\\pi$ learning method is model-free and makes primal-dual updates to the policy and value vectors as new data are revealed. For infinite-horizon undiscounted Markov decision process with finite state space $S$ and finite action spa","authors_text":"Mengdi Wang","cross_cats":["cs.CC","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T05:03:19Z","title":"Primal-Dual $\\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06100","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":"sha256:6c8d8c1817c551e9d4438ea2d441ddf7581740513db5ed18eb62d2bf068b40ea","target":"record","created_at":"2026-05-18T00:32:37Z","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":"547f6c00f4bc96be7d9bad78698966495b93a6c9d84bfecfbbdf983a0eec9bfb","cross_cats_sorted":["cs.CC","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T05:03:19Z","title_canon_sha256":"e97062a624e05db64f958f3f5b3f45c9993fbd39c68727ea044d0258c7647c1d"},"schema_version":"1.0","source":{"id":"1710.06100","kind":"arxiv","version":1}},"canonical_sha256":"12ed6bb2b32c55770016e82e35f55fbc9543ee1eb38fe19db74caec5a53b5c96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ed6bb2b32c55770016e82e35f55fbc9543ee1eb38fe19db74caec5a53b5c96","first_computed_at":"2026-05-18T00:32:37.738354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:37.738354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cu5FQpGyPI1zPti6mx42iPJqA2hsmeEwMzd+nm99v7VnSMOnnfM67/6IvvHWQn6v3nHJth/0hA4GumvLtXY9BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:37.739177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.06100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c8d8c1817c551e9d4438ea2d441ddf7581740513db5ed18eb62d2bf068b40ea","sha256:8dca70c3e71fb4de7031e7a7b136e4ccc1f3c5684202771cad19f3379e902616"],"state_sha256":"87a043b3eb88711150f9c34c8ba3a2a20ac065ac94b7b811de62e15709a4d7ee"}