{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:OJ4GYU5BCLMCA7GDQGRGB366OK","short_pith_number":"pith:OJ4GYU5B","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"},"canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","source":{"kind":"arxiv","id":"1307.5118","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:OJ4GYU5BCLMCA7GDQGRGB366OK","target":"record","payload":{"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"},"canonical_sha256":"72786c53a112d8207cc381a260efde729f403f396115d660fa997f35ba83bf65","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"},"source_kind":"arxiv","source_id":"1307.5118","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:18:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2XTj0mj1sUNMNcrWPlkRt2ItMnJG7W1cQsFYheXGFHuVSJLe72UU/f0YH22WjdZK3T2x31fRcyEq9yyNGrZICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:48:23.422599Z"},"content_sha256":"d5297cad48618fdbe8c17a5ab04dc6b9182daa663a247d46ae000147b66577aa","schema_version":"1.0","event_id":"sha256:d5297cad48618fdbe8c17a5ab04dc6b9182daa663a247d46ae000147b66577aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:OJ4GYU5BCLMCA7GDQGRGB366OK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:18:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3FrHYlU8NgLp+M/NeKk/RRxzS3Ug65CNoH7KP2ITkA0FxCw0F2EhPJsuOhWpVMam5ByfeaJC+BNTpRQBwPHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:48:23.423245Z"},"content_sha256":"fd3742e3220ca7ccf1ae40451c144c890d55eb296f090168b328f03832ad2dcd","schema_version":"1.0","event_id":"sha256:fd3742e3220ca7ccf1ae40451c144c890d55eb296f090168b328f03832ad2dcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/bundle.json","state_url":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T20:48:23Z","links":{"resolver":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK","bundle":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/bundle.json","state":"https://pith.science/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJ4GYU5BCLMCA7GDQGRGB366OK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KU5uVx1gYjsMyhePBMtt8vy8EjRTPR+MFWQGO13e1MOjD0Zme7rSCBNeh6zaYBkTIWrwE0rny0BTh/FpR+7EBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:48:23.426501Z","bundle_sha256":"afb34064be90458e1be3e9cbdcb7bc1fb7adffedd6e61a5a0aebcf713d944923"}}