{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ISE3X7VDZQTAUBHOHP4BFIJ2EY","short_pith_number":"pith:ISE3X7VD","schema_version":"1.0","canonical_sha256":"4489bbfea3cc260a04ee3bf812a13a263673a4f818edf66cdffa5eb6fe77705c","source":{"kind":"arxiv","id":"1512.05509","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Denis Steckelmacher, Peter Vrancx","submitted_at":"2015-12-17T09:45:51Z","abstract_excerpt":"This paper explores the performance of fitted neural Q iteration for reinforcement learning in several partially observable environments, using three recurrent neural network architectures: Long Short-Term Memory, Gated Recurrent Unit and MUT1, a recurrent neural architecture evolved from a pool of several thousands candidate architectures. A variant of fitted Q iteration, based on Advantage values instead of Q values, is also explored. The results show that GRU performs significantly better than LSTM and MUT1 for most of the problems considered, requiring less training episodes and less CPU t"},"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":"1512.05509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-12-17T09:45:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"551fe871ab665cb25f4cebf713392b9d747f409ee9dd70de604a1a5c45b0c29b","abstract_canon_sha256":"d2fd4e2e926756ca0848006070481d149ba99a6386ff771da192804e205fe7d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:09.909738Z","signature_b64":"S5+pZE+RzRRAJjzL7pIynXkNQZzYgkz7RG/1rrdQbnLpruAO1uekfp4e049eKcrft+6FkiawhmblGs3qA+gRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4489bbfea3cc260a04ee3bf812a13a263673a4f818edf66cdffa5eb6fe77705c","last_reissued_at":"2026-05-18T01:24:09.909186Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:09.909186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Denis Steckelmacher, Peter Vrancx","submitted_at":"2015-12-17T09:45:51Z","abstract_excerpt":"This paper explores the performance of fitted neural Q iteration for reinforcement learning in several partially observable environments, using three recurrent neural network architectures: Long Short-Term Memory, Gated Recurrent Unit and MUT1, a recurrent neural architecture evolved from a pool of several thousands candidate architectures. A variant of fitted Q iteration, based on Advantage values instead of Q values, is also explored. The results show that GRU performs significantly better than LSTM and MUT1 for most of the problems considered, requiring less training episodes and less CPU t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05509","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":"1512.05509","created_at":"2026-05-18T01:24:09.909278+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.05509v1","created_at":"2026-05-18T01:24:09.909278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05509","created_at":"2026-05-18T01:24:09.909278+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISE3X7VDZQTA","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISE3X7VDZQTAUBHO","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISE3X7VD","created_at":"2026-05-18T12:29:25.134429+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/ISE3X7VDZQTAUBHOHP4BFIJ2EY","json":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY.json","graph_json":"https://pith.science/api/pith-number/ISE3X7VDZQTAUBHOHP4BFIJ2EY/graph.json","events_json":"https://pith.science/api/pith-number/ISE3X7VDZQTAUBHOHP4BFIJ2EY/events.json","paper":"https://pith.science/paper/ISE3X7VD"},"agent_actions":{"view_html":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY","download_json":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY.json","view_paper":"https://pith.science/paper/ISE3X7VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.05509&json=true","fetch_graph":"https://pith.science/api/pith-number/ISE3X7VDZQTAUBHOHP4BFIJ2EY/graph.json","fetch_events":"https://pith.science/api/pith-number/ISE3X7VDZQTAUBHOHP4BFIJ2EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY/action/storage_attestation","attest_author":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY/action/author_attestation","sign_citation":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY/action/citation_signature","submit_replication":"https://pith.science/pith/ISE3X7VDZQTAUBHOHP4BFIJ2EY/action/replication_record"}},"created_at":"2026-05-18T01:24:09.909278+00:00","updated_at":"2026-05-18T01:24:09.909278+00:00"}