{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:OJ4GYU5BCLMCA7GDQGRGB366OK","short_pith_number":"pith:OJ4GYU5B","schema_version":"1.0","canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","source":{"kind":"arxiv","id":"1307.5118","version":1},"attestation_state":"computed","paper":{"title":"Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jun Morimoto, Masashi Sugiyama, Syogo Mori, Tingting Zhao, Voot Tangkaratt","submitted_at":"2013-07-19T03:00:39Z","abstract_excerpt":"The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, collecting a large number of samples is often expensive in practice. On the other hand, the model-based RL approach first estimates the transition model of the environment and then learns the policy based on the estimated transition model. Thus, if the transition model is accurate"},"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":"1307.5118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-07-19T03:00:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c02b1ca73de814fd0ecc6f342cf02f2c98cc404eee94ff7a2b8369de3ad92cc","abstract_canon_sha256":"865cbb64f5d74829d1e4e41072347caca78ac909649b9ca391e658d0535eac2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:18:05.641762Z","signature_b64":"ojYvk6dAnW6CsK0a9kJx/mdVVtczGEcPaWc1CObcFdcI6/oPONYYBLk5PKsuVKBwxCz/KWL+Iit62cKhZ/3SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","last_reissued_at":"2026-05-18T03:18:05.641098Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:18:05.641098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jun Morimoto, Masashi Sugiyama, Syogo Mori, Tingting Zhao, Voot Tangkaratt","submitted_at":"2013-07-19T03:00:39Z","abstract_excerpt":"The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, collecting a large number of samples is often expensive in practice. On the other hand, the model-based RL approach first estimates the transition model of the environment and then learns the policy based on the estimated transition model. Thus, if the transition model is accurate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.5118","kind":"arxiv","version":1},"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":"1307.5118","created_at":"2026-05-18T03:18:05.641199+00:00"},{"alias_kind":"arxiv_version","alias_value":"1307.5118v1","created_at":"2026-05-18T03:18:05.641199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.5118","created_at":"2026-05-18T03:18:05.641199+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ4GYU5BCLMC","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ4GYU5BCLMCA7GD","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ4GYU5B","created_at":"2026-05-18T12:27:54.935989+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/OJ4GYU5BCLMCA7GDQGRGB366OK","json":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK.json","graph_json":"https://pith.science/api/pith-number/OJ4GYU5BCLMCA7GDQGRGB366OK/graph.json","events_json":"https://pith.science/api/pith-number/OJ4GYU5BCLMCA7GDQGRGB366OK/events.json","paper":"https://pith.science/paper/OJ4GYU5B"},"agent_actions":{"view_html":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK","download_json":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK.json","view_paper":"https://pith.science/paper/OJ4GYU5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1307.5118&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ4GYU5BCLMCA7GDQGRGB366OK/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ4GYU5BCLMCA7GDQGRGB366OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/action/storage_attestation","attest_author":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/action/author_attestation","sign_citation":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/action/citation_signature","submit_replication":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/action/replication_record"}},"created_at":"2026-05-18T03:18:05.641199+00:00","updated_at":"2026-05-18T03:18:05.641199+00:00"}