{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:INVXC2YHEGJMGFRY4URUSFCDLW","short_pith_number":"pith:INVXC2YH","schema_version":"1.0","canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","source":{"kind":"arxiv","id":"1806.01265","version":2},"attestation_state":"computed","paper":{"title":"Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dipendra Misra, Evan Cater, Kavosh Asadi, Michael L. Littman","submitted_at":"2018-06-01T21:54:18Z","abstract_excerpt":"Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying the loss function can have a remarkable impact on effectiveness of planning. Recently Farahmand et al. (2017) proposed a value-aware model learning (VAML) objective that captures the structure of value function during model learning. Using tools from Asadi et al. (2018), we show 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":"1806.01265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-01T21:54:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ec2ccf810a0e0eaddee84cddb8516eff69457ef313127ebd5bdeddb82c373208","abstract_canon_sha256":"1cb5fce260fa176a1a2fd185d4e380ab417ffecc1785e804942306ca57140639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:17.256668Z","signature_b64":"ow0jThKltcbwAKrIozh+sYhK1i7M+afxhHgRWw81tOXeEXgd/aLd9LICxGNEoQd3HYRxTKtSB2ynhNLBQ04vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436b716b072192c31638e5234914435dbe93ab7f4ecf9046126573c8e2bb5f39","last_reissued_at":"2026-05-18T00:11:17.255892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:17.255892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dipendra Misra, Evan Cater, Kavosh Asadi, Michael L. Littman","submitted_at":"2018-06-01T21:54:18Z","abstract_excerpt":"Learning a generative model is a key component of model-based reinforcement learning. Though learning a good model in the tabular setting is a simple task, learning a useful model in the approximate setting is challenging. In this context, an important question is the loss function used for model learning as varying the loss function can have a remarkable impact on effectiveness of planning. Recently Farahmand et al. (2017) proposed a value-aware model learning (VAML) objective that captures the structure of value function during model learning. Using tools from Asadi et al. (2018), we show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01265","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":"1806.01265","created_at":"2026-05-18T00:11:17.256019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01265v2","created_at":"2026-05-18T00:11:17.256019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01265","created_at":"2026-05-18T00:11:17.256019+00:00"},{"alias_kind":"pith_short_12","alias_value":"INVXC2YHEGJM","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"INVXC2YHEGJMGFRY","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"INVXC2YH","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06732","citing_title":"On Training in Imagination","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06732","citing_title":"On Training in Imagination","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW","json":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW.json","graph_json":"https://pith.science/api/pith-number/INVXC2YHEGJMGFRY4URUSFCDLW/graph.json","events_json":"https://pith.science/api/pith-number/INVXC2YHEGJMGFRY4URUSFCDLW/events.json","paper":"https://pith.science/paper/INVXC2YH"},"agent_actions":{"view_html":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW","download_json":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW.json","view_paper":"https://pith.science/paper/INVXC2YH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01265&json=true","fetch_graph":"https://pith.science/api/pith-number/INVXC2YHEGJMGFRY4URUSFCDLW/graph.json","fetch_events":"https://pith.science/api/pith-number/INVXC2YHEGJMGFRY4URUSFCDLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/action/storage_attestation","attest_author":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/action/author_attestation","sign_citation":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/action/citation_signature","submit_replication":"https://pith.science/pith/INVXC2YHEGJMGFRY4URUSFCDLW/action/replication_record"}},"created_at":"2026-05-18T00:11:17.256019+00:00","updated_at":"2026-05-18T00:11:17.256019+00:00"}