{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:E4ENK52EJGOBVFYDLRNI4FJALA","short_pith_number":"pith:E4ENK52E","schema_version":"1.0","canonical_sha256":"2708d57744499c1a97035c5a8e15205814c28eebcc7d5638dafef2fe02fda033","source":{"kind":"arxiv","id":"1811.00128","version":1},"attestation_state":"computed","paper":{"title":"Towards a Simple Approach to Multi-step 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":"2018-10-31T21:31:59Z","abstract_excerpt":"When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes. Model-based agents typically learn a single-step transition model. In this paper, we propose a multi-step model that predicts the outcome of an action sequence with variable length. We show that this model is easy to learn, and that the model can make policy-conditional predictions. We report preliminary results that show a clear advantage for the multi-step model compared to its one-step counterpart."},"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":"1811.00128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T21:31:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0a24a0d2bcb882ea0109229acac857a04eb09366e4bb2a4ef8970b38820c2557","abstract_canon_sha256":"c8297019ae022eb220a039a5fe40a03d1dc229e984c22245d544e08ad41c4444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.153020Z","signature_b64":"8u6NwcF9W+AYjXoD21EGT9IpIP49cmGD4qOuU2t/LFLvDCKMpcNouAmuOnIo/Cfjh1XxSttHiIS6ersVnBlyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2708d57744499c1a97035c5a8e15205814c28eebcc7d5638dafef2fe02fda033","last_reissued_at":"2026-05-18T00:01:48.152379Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.152379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Simple Approach to Multi-step 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":"2018-10-31T21:31:59Z","abstract_excerpt":"When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes. Model-based agents typically learn a single-step transition model. In this paper, we propose a multi-step model that predicts the outcome of an action sequence with variable length. We show that this model is easy to learn, and that the model can make policy-conditional predictions. We report preliminary results that show a clear advantage for the multi-step model compared to its one-step counterpart."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00128","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":"1811.00128","created_at":"2026-05-18T00:01:48.152501+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00128v1","created_at":"2026-05-18T00:01:48.152501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00128","created_at":"2026-05-18T00:01:48.152501+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4ENK52EJGOB","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4ENK52EJGOBVFYD","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4ENK52E","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":217,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA","json":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA.json","graph_json":"https://pith.science/api/pith-number/E4ENK52EJGOBVFYDLRNI4FJALA/graph.json","events_json":"https://pith.science/api/pith-number/E4ENK52EJGOBVFYDLRNI4FJALA/events.json","paper":"https://pith.science/paper/E4ENK52E"},"agent_actions":{"view_html":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA","download_json":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA.json","view_paper":"https://pith.science/paper/E4ENK52E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00128&json=true","fetch_graph":"https://pith.science/api/pith-number/E4ENK52EJGOBVFYDLRNI4FJALA/graph.json","fetch_events":"https://pith.science/api/pith-number/E4ENK52EJGOBVFYDLRNI4FJALA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA/action/storage_attestation","attest_author":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA/action/author_attestation","sign_citation":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA/action/citation_signature","submit_replication":"https://pith.science/pith/E4ENK52EJGOBVFYDLRNI4FJALA/action/replication_record"}},"created_at":"2026-05-18T00:01:48.152501+00:00","updated_at":"2026-05-18T00:01:48.152501+00:00"}