{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EJB73BZCGL65XDBC4WP7CKGD7M","short_pith_number":"pith:EJB73BZC","schema_version":"1.0","canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","source":{"kind":"arxiv","id":"1801.07440","version":2},"attestation_state":"computed","paper":{"title":"Curiosity-driven reinforcement learning with homeostatic regulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ildefons Magrans de Abril, Ryota Kanai","submitted_at":"2018-01-23T08:52:22Z","abstract_excerpt":"We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional homeostatic drive to enhance the overall information gain of a reinforcement learning agent interacting with a complex environment using continuous actions. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of information gain and ii) to simplify the computation of the local rewards by avoiding the approximation of comple"},"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":"1801.07440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-23T08:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"27896d83833a11ac8cbda5c0a3743da7abbb3a98160948000822f74a851d66d6","abstract_canon_sha256":"2cd63b9a854f69bccd323261327de9fc3746e41d8efe41f02a75506498c2e29c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:09.398241Z","signature_b64":"PqMTDq1ajq7watUpwty4W2+a5VotHCJluzT6Qp/7vpfiuYxHiib6gNzffdXPzEOVlqcXLteYkhwKKhlRPCKTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2243fd872232fddb8c22e59ff128c3fb21034f9882cb8bb522e2cf429c608a68","last_reissued_at":"2026-05-18T00:24:09.397503Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:09.397503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curiosity-driven reinforcement learning with homeostatic regulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ildefons Magrans de Abril, Ryota Kanai","submitted_at":"2018-01-23T08:52:22Z","abstract_excerpt":"We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional homeostatic drive to enhance the overall information gain of a reinforcement learning agent interacting with a complex environment using continuous actions. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of information gain and ii) to simplify the computation of the local rewards by avoiding the approximation of comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07440","kind":"arxiv","version":2},"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":"1801.07440","created_at":"2026-05-18T00:24:09.397633+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.07440v2","created_at":"2026-05-18T00:24:09.397633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07440","created_at":"2026-05-18T00:24:09.397633+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJB73BZCGL65","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJB73BZCGL65XDBC","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJB73BZC","created_at":"2026-05-18T12:32:22.470017+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/EJB73BZCGL65XDBC4WP7CKGD7M","json":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M.json","graph_json":"https://pith.science/api/pith-number/EJB73BZCGL65XDBC4WP7CKGD7M/graph.json","events_json":"https://pith.science/api/pith-number/EJB73BZCGL65XDBC4WP7CKGD7M/events.json","paper":"https://pith.science/paper/EJB73BZC"},"agent_actions":{"view_html":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M","download_json":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M.json","view_paper":"https://pith.science/paper/EJB73BZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.07440&json=true","fetch_graph":"https://pith.science/api/pith-number/EJB73BZCGL65XDBC4WP7CKGD7M/graph.json","fetch_events":"https://pith.science/api/pith-number/EJB73BZCGL65XDBC4WP7CKGD7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/action/storage_attestation","attest_author":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/action/author_attestation","sign_citation":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/action/citation_signature","submit_replication":"https://pith.science/pith/EJB73BZCGL65XDBC4WP7CKGD7M/action/replication_record"}},"created_at":"2026-05-18T00:24:09.397633+00:00","updated_at":"2026-05-18T00:24:09.397633+00:00"}