{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TLEJESZ2G6CNFGQTUUNNBYADOC","short_pith_number":"pith:TLEJESZ2","schema_version":"1.0","canonical_sha256":"9ac8924b3a3784d29a13a51ad0e00370b24dbc7d20e01e7c7c4e3a62c8b9e65a","source":{"kind":"arxiv","id":"2012.11293","version":1},"attestation_state":"computed","paper":{"title":"Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"AkshatKumar Nigam, Alan Aspuru-Guzik, Luca A. Thiede, Mario Krenn","submitted_at":"2020-12-17T17:21:59Z","abstract_excerpt":"Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace. Reinforcement learning is a particularly promising approach since it allows for molecular design without prior knowledge. However, the search space is vast and efficient exploration is desirable when using reinforcement learning agents. In this study, we propose an algorithm to aid efficient exploration. The algorithm is inspired by a concept known in the literature as "},"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":"2012.11293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T17:21:59Z","cross_cats_sorted":["cs.AI","physics.chem-ph"],"title_canon_sha256":"dd4744bb2f21ff7be13a90aa62666afe33b0df1492acac4f6effc21569e91a52","abstract_canon_sha256":"701286d4fed779fb598335e2c732b60d4e021973b6a30d6e4a5c9e3d1a987c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:10.532834Z","signature_b64":"l1LhGE4gyen4oKHKqlsGpzgl2Nrx39D1QzcixfeVE6JOBIvmdfV1ko39/THqrqYa9D+R+lnq2WjyHDYjKdDtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ac8924b3a3784d29a13a51ad0e00370b24dbc7d20e01e7c7c4e3a62c8b9e65a","last_reissued_at":"2026-07-05T04:46:10.532487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:10.532487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"AkshatKumar Nigam, Alan Aspuru-Guzik, Luca A. Thiede, Mario Krenn","submitted_at":"2020-12-17T17:21:59Z","abstract_excerpt":"Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace. Reinforcement learning is a particularly promising approach since it allows for molecular design without prior knowledge. However, the search space is vast and efficient exploration is desirable when using reinforcement learning agents. In this study, we propose an algorithm to aid efficient exploration. The algorithm is inspired by a concept known in the literature as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11293","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.11293/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2012.11293","created_at":"2026-07-05T04:46:10.532543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11293v1","created_at":"2026-07-05T04:46:10.532543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11293","created_at":"2026-07-05T04:46:10.532543+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLEJESZ2G6CN","created_at":"2026-07-05T04:46:10.532543+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLEJESZ2G6CNFGQT","created_at":"2026-07-05T04:46:10.532543+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLEJESZ2","created_at":"2026-07-05T04:46:10.532543+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/TLEJESZ2G6CNFGQTUUNNBYADOC","json":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC.json","graph_json":"https://pith.science/api/pith-number/TLEJESZ2G6CNFGQTUUNNBYADOC/graph.json","events_json":"https://pith.science/api/pith-number/TLEJESZ2G6CNFGQTUUNNBYADOC/events.json","paper":"https://pith.science/paper/TLEJESZ2"},"agent_actions":{"view_html":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC","download_json":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC.json","view_paper":"https://pith.science/paper/TLEJESZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11293&json=true","fetch_graph":"https://pith.science/api/pith-number/TLEJESZ2G6CNFGQTUUNNBYADOC/graph.json","fetch_events":"https://pith.science/api/pith-number/TLEJESZ2G6CNFGQTUUNNBYADOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC/action/storage_attestation","attest_author":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC/action/author_attestation","sign_citation":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC/action/citation_signature","submit_replication":"https://pith.science/pith/TLEJESZ2G6CNFGQTUUNNBYADOC/action/replication_record"}},"created_at":"2026-07-05T04:46:10.532543+00:00","updated_at":"2026-07-05T04:46:10.532543+00:00"}