{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:72MAJYYUYE4UDEW7LOIM5E3Q6C","short_pith_number":"pith:72MAJYYU","schema_version":"1.0","canonical_sha256":"fe9804e314c1394192df5b90ce9370f0be3fea1eab131400e2871ae83b3632cb","source":{"kind":"arxiv","id":"1901.02577","version":1},"attestation_state":"computed","paper":{"title":"Robust and Adaptive Planning under Model Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Apoorva Sharma, James Harrison, Marco Pavone, Matthew Tsao","submitted_at":"2019-01-09T01:32:43Z","abstract_excerpt":"Planning under model uncertainty is a fundamental problem across many applications of decision making and learning. In this paper, we propose the Robust Adaptive Monte Carlo Planning (RAMCP) algorithm, which allows computation of risk-sensitive Bayes-adaptive policies that optimally trade off exploration, exploitation, and robustness. RAMCP formulates the risk-sensitive planning problem as a two-player zero-sum game, in which an adversary perturbs the agent's belief over the models. We introduce two versions of the RAMCP algorithm. The first, RAMCP-F, converges to an optimal risk-sensitive pol"},"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":"1901.02577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-01-09T01:32:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1814370ab9467955100baafb0741e796ea73a4ed4a4fd9041d9a380535cc4a4","abstract_canon_sha256":"1f13091304607b71743ec907aa6035ef274a5e1d156a5333e4cf212c007e43a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:40.095335Z","signature_b64":"jWeQsoX23OhZ26L9AmMM93LGhr6pZ9iBl/C2lgNk6VM6RZqWQmlqcrpKpifaoCsio303ircZcDXo2Q7CpqsfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9804e314c1394192df5b90ce9370f0be3fea1eab131400e2871ae83b3632cb","last_reissued_at":"2026-05-17T23:56:40.094613Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:40.094613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Adaptive Planning under Model Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Apoorva Sharma, James Harrison, Marco Pavone, Matthew Tsao","submitted_at":"2019-01-09T01:32:43Z","abstract_excerpt":"Planning under model uncertainty is a fundamental problem across many applications of decision making and learning. In this paper, we propose the Robust Adaptive Monte Carlo Planning (RAMCP) algorithm, which allows computation of risk-sensitive Bayes-adaptive policies that optimally trade off exploration, exploitation, and robustness. RAMCP formulates the risk-sensitive planning problem as a two-player zero-sum game, in which an adversary perturbs the agent's belief over the models. We introduce two versions of the RAMCP algorithm. The first, RAMCP-F, converges to an optimal risk-sensitive pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02577","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":"1901.02577","created_at":"2026-05-17T23:56:40.094722+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02577v1","created_at":"2026-05-17T23:56:40.094722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02577","created_at":"2026-05-17T23:56:40.094722+00:00"},{"alias_kind":"pith_short_12","alias_value":"72MAJYYUYE4U","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"72MAJYYUYE4UDEW7","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"72MAJYYU","created_at":"2026-05-18T12:33:10.108867+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/72MAJYYUYE4UDEW7LOIM5E3Q6C","json":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C.json","graph_json":"https://pith.science/api/pith-number/72MAJYYUYE4UDEW7LOIM5E3Q6C/graph.json","events_json":"https://pith.science/api/pith-number/72MAJYYUYE4UDEW7LOIM5E3Q6C/events.json","paper":"https://pith.science/paper/72MAJYYU"},"agent_actions":{"view_html":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C","download_json":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C.json","view_paper":"https://pith.science/paper/72MAJYYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02577&json=true","fetch_graph":"https://pith.science/api/pith-number/72MAJYYUYE4UDEW7LOIM5E3Q6C/graph.json","fetch_events":"https://pith.science/api/pith-number/72MAJYYUYE4UDEW7LOIM5E3Q6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C/action/storage_attestation","attest_author":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C/action/author_attestation","sign_citation":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C/action/citation_signature","submit_replication":"https://pith.science/pith/72MAJYYUYE4UDEW7LOIM5E3Q6C/action/replication_record"}},"created_at":"2026-05-17T23:56:40.094722+00:00","updated_at":"2026-05-17T23:56:40.094722+00:00"}