{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QXLP7LLAJ3EY2MFHR6WRNLYXPP","short_pith_number":"pith:QXLP7LLA","schema_version":"1.0","canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","source":{"kind":"arxiv","id":"1706.01417","version":1},"attestation_state":"computed","paper":{"title":"A method for the online construction of the set of states of a Markov Decision Process using Answer Set Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","submitted_at":"2017-06-05T16:48:23Z","abstract_excerpt":"Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set Programming (ASP), named {\\em Online ASP for MDP} (oASP(MDP)), which is a method capable of constructing the set of domain states while the agent interacts with a changing environment. oASP(MDP) updates previously obtained policies, learnt by means of Reinforcement Learning (RL), using rules that represent the domain changes observed by the agent. These rule"},"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":"1706.01417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"f24b94a7168b0f719560c9e9430315783d90f0193bb3bf529fa10dd3f5a2abbf","abstract_canon_sha256":"45aae3ba42ad908e33cb5185406590b724ae391f578e3a40a1e65070ff0c4915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:03.633946Z","signature_b64":"7IFIhiwUKA4KVMp48BsCVuLfiJqXHjraDcfNA9Ac2UAiUYuqo2qvifTkVEu6qMnhBMhnXF4kAI7EDgWIHxPwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","last_reissued_at":"2026-05-18T00:43:03.633282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:03.633282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A method for the online construction of the set of states of a Markov Decision Process using Answer Set Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","submitted_at":"2017-06-05T16:48:23Z","abstract_excerpt":"Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set Programming (ASP), named {\\em Online ASP for MDP} (oASP(MDP)), which is a method capable of constructing the set of domain states while the agent interacts with a changing environment. oASP(MDP) updates previously obtained policies, learnt by means of Reinforcement Learning (RL), using rules that represent the domain changes observed by the agent. These rule"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01417","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":"1706.01417","created_at":"2026-05-18T00:43:03.633370+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01417v1","created_at":"2026-05-18T00:43:03.633370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01417","created_at":"2026-05-18T00:43:03.633370+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXLP7LLAJ3EY","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXLP7LLAJ3EY2MFH","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXLP7LLA","created_at":"2026-05-18T12:31:39.905425+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/QXLP7LLAJ3EY2MFHR6WRNLYXPP","json":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP.json","graph_json":"https://pith.science/api/pith-number/QXLP7LLAJ3EY2MFHR6WRNLYXPP/graph.json","events_json":"https://pith.science/api/pith-number/QXLP7LLAJ3EY2MFHR6WRNLYXPP/events.json","paper":"https://pith.science/paper/QXLP7LLA"},"agent_actions":{"view_html":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP","download_json":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP.json","view_paper":"https://pith.science/paper/QXLP7LLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01417&json=true","fetch_graph":"https://pith.science/api/pith-number/QXLP7LLAJ3EY2MFHR6WRNLYXPP/graph.json","fetch_events":"https://pith.science/api/pith-number/QXLP7LLAJ3EY2MFHR6WRNLYXPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/action/storage_attestation","attest_author":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/action/author_attestation","sign_citation":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/action/citation_signature","submit_replication":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/action/replication_record"}},"created_at":"2026-05-18T00:43:03.633370+00:00","updated_at":"2026-05-18T00:43:03.633370+00:00"}