{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6BX7JZ5NTKCEUUTHULEAYYTYPJ","short_pith_number":"pith:6BX7JZ5N","schema_version":"1.0","canonical_sha256":"f06ff4e7ad9a844a5267a2c80c62787a52593cdf5312fb24a041780399180c2c","source":{"kind":"arxiv","id":"1708.01867","version":5},"attestation_state":"computed","paper":{"title":"An Information-Theoretic Optimality Principle for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Felix Leibfried, Haitham Bou-Ammar, Jordi Grau-Moya","submitted_at":"2017-08-06T09:23:22Z","abstract_excerpt":"We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates. The resultant algorithm encompasses a wide range of learning outcomes containing deep Q-networks as a special case. Different learning outcomes can be demonstrated by tuning a Lagrange multiplier accordingly. We furthermore propose a novel scheduling scheme for this Lagrange multiplier to ensure efficient and robust learni"},"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":"1708.01867","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-06T09:23:22Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1ca35bd1b6d2cd3fbe76cfd5aaffd022a3fc4b03a04aab81f3147aac9eea615f","abstract_canon_sha256":"5ace951ff1cfd1697253dfc5c045196fde4751f5b5720cd4c2f6fd6d6efe250a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:22.528654Z","signature_b64":"3KitOKRhxVbXNCgKAgVYPWHCDWACQxQMeaaETvmfaQhS/TT6XZsidfopPyOoJDCY1dduKVxZCVahKUL/QImKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06ff4e7ad9a844a5267a2c80c62787a52593cdf5312fb24a041780399180c2c","last_reissued_at":"2026-05-18T00:00:22.527945Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:22.527945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information-Theoretic Optimality Principle for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Felix Leibfried, Haitham Bou-Ammar, Jordi Grau-Moya","submitted_at":"2017-08-06T09:23:22Z","abstract_excerpt":"We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from information theory, we introduce an intrinsic penalty signal encouraging reduced Q-value estimates. The resultant algorithm encompasses a wide range of learning outcomes containing deep Q-networks as a special case. Different learning outcomes can be demonstrated by tuning a Lagrange multiplier accordingly. We furthermore propose a novel scheduling scheme for this Lagrange multiplier to ensure efficient and robust learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01867","kind":"arxiv","version":5},"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":"1708.01867","created_at":"2026-05-18T00:00:22.528033+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01867v5","created_at":"2026-05-18T00:00:22.528033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01867","created_at":"2026-05-18T00:00:22.528033+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BX7JZ5NTKCE","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BX7JZ5NTKCEUUTH","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BX7JZ5N","created_at":"2026-05-18T12:31:03.183658+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/6BX7JZ5NTKCEUUTHULEAYYTYPJ","json":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ.json","graph_json":"https://pith.science/api/pith-number/6BX7JZ5NTKCEUUTHULEAYYTYPJ/graph.json","events_json":"https://pith.science/api/pith-number/6BX7JZ5NTKCEUUTHULEAYYTYPJ/events.json","paper":"https://pith.science/paper/6BX7JZ5N"},"agent_actions":{"view_html":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ","download_json":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ.json","view_paper":"https://pith.science/paper/6BX7JZ5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01867&json=true","fetch_graph":"https://pith.science/api/pith-number/6BX7JZ5NTKCEUUTHULEAYYTYPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6BX7JZ5NTKCEUUTHULEAYYTYPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ/action/storage_attestation","attest_author":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ/action/author_attestation","sign_citation":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ/action/citation_signature","submit_replication":"https://pith.science/pith/6BX7JZ5NTKCEUUTHULEAYYTYPJ/action/replication_record"}},"created_at":"2026-05-18T00:00:22.528033+00:00","updated_at":"2026-05-18T00:00:22.528033+00:00"}