{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","short_pith_number":"pith:Q6ILPJUQ","schema_version":"1.0","canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","source":{"kind":"arxiv","id":"1806.05415","version":1},"attestation_state":"computed","paper":{"title":"Configurable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alberto Maria Metelli, Marcello Restelli, Mirco Mutti","submitted_at":"2018-06-14T08:54:38Z","abstract_excerpt":"In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evalua"},"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":"1806.05415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-14T08:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"e2d2806327888403b635b151312c8c89f9e7ed59087d1eac2f0f46c8589a4d50","abstract_canon_sha256":"a8f97e29874161584be851892a0b3d2cf5c04aad47e0f06c5496b29ba44cc781"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.042691Z","signature_b64":"Y/VaRWjoyuDtnJkuA2N07ImJ8my7CuGTLTQoBneYCrgCxHxd6fLEBQwjK8phjhDh9ca84FDwUDr0UTSNmJsaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8790b7a690d677676dc43a0e2826275f902eb54252ba77cebd6b8844f8459357","last_reissued_at":"2026-05-18T00:13:16.041974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.041974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Configurable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alberto Maria Metelli, Marcello Restelli, Mirco Mutti","submitted_at":"2018-06-14T08:54:38Z","abstract_excerpt":"In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05415","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":"1806.05415","created_at":"2026-05-18T00:13:16.042079+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05415v1","created_at":"2026-05-18T00:13:16.042079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05415","created_at":"2026-05-18T00:13:16.042079+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6ILPJUQ2Z3W","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6ILPJUQ2Z3WO3OE","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6ILPJUQ","created_at":"2026-05-18T12:32:46.962924+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/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","json":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6.json","graph_json":"https://pith.science/api/pith-number/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/graph.json","events_json":"https://pith.science/api/pith-number/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/events.json","paper":"https://pith.science/paper/Q6ILPJUQ"},"agent_actions":{"view_html":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6","download_json":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6.json","view_paper":"https://pith.science/paper/Q6ILPJUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05415&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/action/storage_attestation","attest_author":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/action/author_attestation","sign_citation":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/action/citation_signature","submit_replication":"https://pith.science/pith/Q6ILPJUQ2Z3WO3OEHIHCQJRHL6/action/replication_record"}},"created_at":"2026-05-18T00:13:16.042079+00:00","updated_at":"2026-05-18T00:13:16.042079+00:00"}