{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:OJ4GYU5BCLMCA7GDQGRGB366OK","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":"865cbb64f5d74829d1e4e41072347caca78ac909649b9ca391e658d0535eac2f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-07-19T03:00:39Z","title_canon_sha256":"1c02b1ca73de814fd0ecc6f342cf02f2c98cc404eee94ff7a2b8369de3ad92cc"},"schema_version":"1.0","source":{"id":"1307.5118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.5118","created_at":"2026-05-18T03:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"1307.5118v1","created_at":"2026-05-18T03:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.5118","created_at":"2026-05-18T03:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"OJ4GYU5BCLMC","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"OJ4GYU5BCLMCA7GD","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"OJ4GYU5B","created_at":"2026-05-18T12:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:fd3742e3220ca7ccf1ae40451c144c890d55eb296f090168b328f03832ad2dcd","target":"graph","created_at":"2026-05-18T03:18:05Z","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":"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","authors_text":"Jun Morimoto, Masashi Sugiyama, Syogo Mori, Tingting Zhao, Voot Tangkaratt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-07-19T03:00:39Z","title":"Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.5118","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:d5297cad48618fdbe8c17a5ab04dc6b9182daa663a247d46ae000147b66577aa","target":"record","created_at":"2026-05-18T03:18:05Z","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":"865cbb64f5d74829d1e4e41072347caca78ac909649b9ca391e658d0535eac2f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-07-19T03:00:39Z","title_canon_sha256":"1c02b1ca73de814fd0ecc6f342cf02f2c98cc404eee94ff7a2b8369de3ad92cc"},"schema_version":"1.0","source":{"id":"1307.5118","kind":"arxiv","version":1}},"canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","first_computed_at":"2026-05-18T03:18:05.641098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:18:05.641098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ojYvk6dAnW6CsK0a9kJx/mdVVtczGEcPaWc1CObcFdcI6/oPONYYBLk5PKsuVKBwxCz/KWL+Iit62cKhZ/3SAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:18:05.641762Z","signed_message":"canonical_sha256_bytes"},"source_id":"1307.5118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5297cad48618fdbe8c17a5ab04dc6b9182daa663a247d46ae000147b66577aa","sha256:fd3742e3220ca7ccf1ae40451c144c890d55eb296f090168b328f03832ad2dcd"],"state_sha256":"d61465b44c6338bbfde0194ce30acb1b693a6f07d9147ad33f16704444b1427b"}