{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QW6OBNOLMFB4GXEFCSSXLLR7N4","short_pith_number":"pith:QW6OBNOL","schema_version":"1.0","canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","source":{"kind":"arxiv","id":"1803.01118","version":2},"attestation_state":"computed","paper":{"title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bradly C. Stadie, Ge Yang, Ilya Sutskever, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu","submitted_at":"2018-03-03T07:13:43Z","abstract_excerpt":"We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\\text{RL}^2$. Results are presented on a novel environment we call `Krazy World' and a set of maze environments. We show E-MAML and E-$\\text{RL}^2$ deliver better performance on tasks where exploration is important."},"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":"1803.01118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-03T07:13:43Z","cross_cats_sorted":[],"title_canon_sha256":"cfa9409316379d81c269af3f59045f1cfd8a5b4bc10b72cd91ea5258b3fbc596","abstract_canon_sha256":"67567713d3af65d196af8878aa60d9334b23d48a31e0bc3bbf61533ab643d927"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:29.955639Z","signature_b64":"1Kx52nQTDUWRb8PiL7dIQNqdCIrsLOTXTHPYXgZzdCFUKi5zKlzSBI9IQNe7r7JFL6mD9Cy5bvK/nm4/P+RhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","last_reissued_at":"2026-05-17T23:56:29.955204Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:29.955204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bradly C. Stadie, Ge Yang, Ilya Sutskever, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu","submitted_at":"2018-03-03T07:13:43Z","abstract_excerpt":"We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\\text{RL}^2$. Results are presented on a novel environment we call `Krazy World' and a set of maze environments. We show E-MAML and E-$\\text{RL}^2$ deliver better performance on tasks where exploration is important."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01118","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":"1803.01118","created_at":"2026-05-17T23:56:29.955279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01118v2","created_at":"2026-05-17T23:56:29.955279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01118","created_at":"2026-05-17T23:56:29.955279+00:00"},{"alias_kind":"pith_short_12","alias_value":"QW6OBNOLMFB4","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QW6OBNOLMFB4GXEF","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QW6OBNOL","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.23448","citing_title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4","json":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4.json","graph_json":"https://pith.science/api/pith-number/QW6OBNOLMFB4GXEFCSSXLLR7N4/graph.json","events_json":"https://pith.science/api/pith-number/QW6OBNOLMFB4GXEFCSSXLLR7N4/events.json","paper":"https://pith.science/paper/QW6OBNOL"},"agent_actions":{"view_html":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4","download_json":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4.json","view_paper":"https://pith.science/paper/QW6OBNOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01118&json=true","fetch_graph":"https://pith.science/api/pith-number/QW6OBNOLMFB4GXEFCSSXLLR7N4/graph.json","fetch_events":"https://pith.science/api/pith-number/QW6OBNOLMFB4GXEFCSSXLLR7N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/action/storage_attestation","attest_author":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/action/author_attestation","sign_citation":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/action/citation_signature","submit_replication":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/action/replication_record"}},"created_at":"2026-05-17T23:56:29.955279+00:00","updated_at":"2026-05-17T23:56:29.955279+00:00"}