{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7MLWNHXFOSVBEFQ3OZKUQQ7MP2","short_pith_number":"pith:7MLWNHXF","schema_version":"1.0","canonical_sha256":"fb17669ee574aa12161b76554843ec7eaf8c1ad92b4285a35f5d94e2c6106f7b","source":{"kind":"arxiv","id":"1710.08012","version":2},"attestation_state":"computed","paper":{"title":"Exploiting generalization in the subspaces for faster model-based learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Majid Nili Ahmadabadi, Maryam Hashemzadeh, Reshad Hosseini","submitted_at":"2017-10-22T20:50:52Z","abstract_excerpt":"Due to the lack of enough generalization in the state-space, common methods in Reinforcement Learning (RL) suffer from slow learning speed especially in the early learning trials. This paper introduces a model-based method in discrete state-spaces for increasing learning speed in terms of required experience (but not required computational time) by exploiting generalization in the experiences of the subspaces. A subspace is formed by choosing a subset of features in the original state representation (full-space). Generalization and faster learning in a subspace are due to many-to-one mapping o"},"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":"1710.08012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-22T20:50:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"09ca9cd9f434f25e82dcbd678dbb224079a9709482946cf2f5eb08c9405ac161","abstract_canon_sha256":"a781fef2588865df02350224b02b1a3bd64b355566711342a57e2bba8e3a35f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:55.501613Z","signature_b64":"AmO/Dxrgqhun8im9QxnOBZMxzuioLkct04tf6dQ2qwyiz+w49AHgda9vFr5NPFx0tTP79gpY0E2xHtqImHm0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb17669ee574aa12161b76554843ec7eaf8c1ad92b4285a35f5d94e2c6106f7b","last_reissued_at":"2026-05-18T00:31:55.501204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:55.501204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting generalization in the subspaces for faster model-based learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Majid Nili Ahmadabadi, Maryam Hashemzadeh, Reshad Hosseini","submitted_at":"2017-10-22T20:50:52Z","abstract_excerpt":"Due to the lack of enough generalization in the state-space, common methods in Reinforcement Learning (RL) suffer from slow learning speed especially in the early learning trials. This paper introduces a model-based method in discrete state-spaces for increasing learning speed in terms of required experience (but not required computational time) by exploiting generalization in the experiences of the subspaces. A subspace is formed by choosing a subset of features in the original state representation (full-space). Generalization and faster learning in a subspace are due to many-to-one mapping o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.08012","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":""},"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":"1710.08012","created_at":"2026-05-18T00:31:55.501266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.08012v2","created_at":"2026-05-18T00:31:55.501266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.08012","created_at":"2026-05-18T00:31:55.501266+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MLWNHXFOSVB","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MLWNHXFOSVBEFQ3","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MLWNHXF","created_at":"2026-05-18T12:31:05.417338+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/7MLWNHXFOSVBEFQ3OZKUQQ7MP2","json":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2.json","graph_json":"https://pith.science/api/pith-number/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/graph.json","events_json":"https://pith.science/api/pith-number/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/events.json","paper":"https://pith.science/paper/7MLWNHXF"},"agent_actions":{"view_html":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2","download_json":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2.json","view_paper":"https://pith.science/paper/7MLWNHXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.08012&json=true","fetch_graph":"https://pith.science/api/pith-number/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/graph.json","fetch_events":"https://pith.science/api/pith-number/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/action/storage_attestation","attest_author":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/action/author_attestation","sign_citation":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/action/citation_signature","submit_replication":"https://pith.science/pith/7MLWNHXFOSVBEFQ3OZKUQQ7MP2/action/replication_record"}},"created_at":"2026-05-18T00:31:55.501266+00:00","updated_at":"2026-05-18T00:31:55.501266+00:00"}