{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZTTPSLJXNLFMRHOVQEC7ADDS4Z","short_pith_number":"pith:ZTTPSLJX","schema_version":"1.0","canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","source":{"kind":"arxiv","id":"2104.07361","version":2},"attestation_state":"computed","paper":{"title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hemanta Makwana, Rahul Madhavan","submitted_at":"2021-04-15T10:37:38Z","abstract_excerpt":"We study the feature-scaled version of the Monte Carlo algorithm with linear function approximation. This algorithm converges to a scale-invariant solution, which is not unduly affected by states having feature vectors with large norms. The usual versions of the MCMC algorithm, obtained by minimizing the least-squares criterion, do not produce solutions that give equal importance to all states irrespective of feature-vector norm -- a requirement that may be critical in many reinforcement learning contexts. To speed up convergence in our algorithm, we introduce an adaptive step-size based on th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.07361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-15T10:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"d29ac2276d2c25aa0e8c9bfc3cc90ca477eee79c36af2f79c223a763418bdb60","abstract_canon_sha256":"6144efbb040f19c754707d28747f9e4cdbc018d98d173e87035ee57179604072"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:05.323115Z","signature_b64":"FNmKkM93Tab+8WLhmKmfib3BT2rYSUEyUOmMDFkI8iA+iB0o7paeqYMTJGVoPS+tGjxbEi8LHVfjsHmss/waBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cce6f92d376acac89dd58105f00c72e66622109acfa8b20ce09f62404f241334","last_reissued_at":"2026-07-05T04:27:05.322710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:05.322710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hemanta Makwana, Rahul Madhavan","submitted_at":"2021-04-15T10:37:38Z","abstract_excerpt":"We study the feature-scaled version of the Monte Carlo algorithm with linear function approximation. This algorithm converges to a scale-invariant solution, which is not unduly affected by states having feature vectors with large norms. The usual versions of the MCMC algorithm, obtained by minimizing the least-squares criterion, do not produce solutions that give equal importance to all states irrespective of feature-vector norm -- a requirement that may be critical in many reinforcement learning contexts. To speed up convergence in our algorithm, we introduce an adaptive step-size based on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07361","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/2104.07361/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.07361","created_at":"2026-07-05T04:27:05.322763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07361v2","created_at":"2026-07-05T04:27:05.322763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07361","created_at":"2026-07-05T04:27:05.322763+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTTPSLJXNLFM","created_at":"2026-07-05T04:27:05.322763+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTTPSLJXNLFMRHOV","created_at":"2026-07-05T04:27:05.322763+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTTPSLJX","created_at":"2026-07-05T04:27:05.322763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z","json":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z.json","graph_json":"https://pith.science/api/pith-number/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/graph.json","events_json":"https://pith.science/api/pith-number/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/events.json","paper":"https://pith.science/paper/ZTTPSLJX"},"agent_actions":{"view_html":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z","download_json":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z.json","view_paper":"https://pith.science/paper/ZTTPSLJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07361&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/action/storage_attestation","attest_author":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/action/author_attestation","sign_citation":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/action/citation_signature","submit_replication":"https://pith.science/pith/ZTTPSLJXNLFMRHOVQEC7ADDS4Z/action/replication_record"}},"created_at":"2026-07-05T04:27:05.322763+00:00","updated_at":"2026-07-05T04:27:05.322763+00:00"}