{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SXF6V2ESHFJFOFVQKGZ7YXSJ5D","short_pith_number":"pith:SXF6V2ES","schema_version":"1.0","canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","source":{"kind":"arxiv","id":"1904.02435","version":2},"attestation_state":"computed","paper":{"title":"Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jim Torresen, Kai Olav Ellefsen","submitted_at":"2019-04-04T09:52:18Z","abstract_excerpt":"A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning arch"},"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":"1904.02435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-04T09:52:18Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"06795c53445fa323763cb5917bf476c64a6885d82247beafe0d13e0dd262869e","abstract_canon_sha256":"4ea13fa73017f6f61175f8601f69559f03adb0598c58db50698a7a7911207cf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:08.912075Z","signature_b64":"LO9ql2RcUMsLP6QTuIiAEiB2l13Ut3iGZUZZW8F/2Taelnto/zr7WsMZkwNW6ubyMNDrURm6QIIUQPH0vdPwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95cbeae89239525716b051b3fc5e49e8c609e79879d65dc3d5d208e801bf88e5","last_reissued_at":"2026-05-17T23:46:08.911496Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:08.911496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jim Torresen, Kai Olav Ellefsen","submitted_at":"2019-04-04T09:52:18Z","abstract_excerpt":"A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02435","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":"1904.02435","created_at":"2026-05-17T23:46:08.911602+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02435v2","created_at":"2026-05-17T23:46:08.911602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02435","created_at":"2026-05-17T23:46:08.911602+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXF6V2ESHFJF","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXF6V2ESHFJFOFVQ","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXF6V2ES","created_at":"2026-05-18T12:33:27.125529+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/SXF6V2ESHFJFOFVQKGZ7YXSJ5D","json":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D.json","graph_json":"https://pith.science/api/pith-number/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/graph.json","events_json":"https://pith.science/api/pith-number/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/events.json","paper":"https://pith.science/paper/SXF6V2ES"},"agent_actions":{"view_html":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D","download_json":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D.json","view_paper":"https://pith.science/paper/SXF6V2ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02435&json=true","fetch_graph":"https://pith.science/api/pith-number/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/graph.json","fetch_events":"https://pith.science/api/pith-number/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/action/storage_attestation","attest_author":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/action/author_attestation","sign_citation":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/action/citation_signature","submit_replication":"https://pith.science/pith/SXF6V2ESHFJFOFVQKGZ7YXSJ5D/action/replication_record"}},"created_at":"2026-05-17T23:46:08.911602+00:00","updated_at":"2026-05-17T23:46:08.911602+00:00"}