{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5ZWFGDO6NAQF6PYCBP3NZAWDRW","short_pith_number":"pith:5ZWFGDO6","schema_version":"1.0","canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","source":{"kind":"arxiv","id":"1912.05500","version":3},"attestation_state":"computed","paper":{"title":"What Can Learned Intrinsic Rewards Capture?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Silver, Hado van Hasselt, Junhyuk Oh, Manuel Kroiss, Matteo Hessel, Satinder Singh, Zeyu Zheng, Zhongwen Xu","submitted_at":"2019-12-11T18:00:05Z","abstract_excerpt":"The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration"},"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":"1912.05500","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d85cb7a27437c796618be3f070a3d5d3e6b01534f5ed7d29cdf634bb216961e","abstract_canon_sha256":"cd08c209207267491f50cf543e6b8cff8d7c616fa465f4adff77329261459f81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:01.816165Z","signature_b64":"550Qh0Z0o2xHEQupu9zQob3g2eY5O8PO02ceO+vIzGGlkfhp+n40k1WjhJ0GKKDqiWKBBkvP5g+0qlx1z9cfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","last_reissued_at":"2026-07-05T01:29:01.815657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:01.815657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Can Learned Intrinsic Rewards Capture?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Silver, Hado van Hasselt, Junhyuk Oh, Manuel Kroiss, Matteo Hessel, Satinder Singh, Zeyu Zheng, Zhongwen Xu","submitted_at":"2019-12-11T18:00:05Z","abstract_excerpt":"The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05500","kind":"arxiv","version":3},"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/1912.05500/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":"1912.05500","created_at":"2026-07-05T01:29:01.815716+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.05500v3","created_at":"2026-07-05T01:29:01.815716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05500","created_at":"2026-07-05T01:29:01.815716+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZWFGDO6NAQF","created_at":"2026-07-05T01:29:01.815716+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZWFGDO6NAQF6PYC","created_at":"2026-07-05T01:29:01.815716+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZWFGDO6","created_at":"2026-07-05T01:29:01.815716+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/5ZWFGDO6NAQF6PYCBP3NZAWDRW","json":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW.json","graph_json":"https://pith.science/api/pith-number/5ZWFGDO6NAQF6PYCBP3NZAWDRW/graph.json","events_json":"https://pith.science/api/pith-number/5ZWFGDO6NAQF6PYCBP3NZAWDRW/events.json","paper":"https://pith.science/paper/5ZWFGDO6"},"agent_actions":{"view_html":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW","download_json":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW.json","view_paper":"https://pith.science/paper/5ZWFGDO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.05500&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZWFGDO6NAQF6PYCBP3NZAWDRW/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZWFGDO6NAQF6PYCBP3NZAWDRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/action/storage_attestation","attest_author":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/action/author_attestation","sign_citation":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/action/citation_signature","submit_replication":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/action/replication_record"}},"created_at":"2026-07-05T01:29:01.815716+00:00","updated_at":"2026-07-05T01:29:01.815716+00:00"}