{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QW6OBNOLMFB4GXEFCSSXLLR7N4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"67567713d3af65d196af8878aa60d9334b23d48a31e0bc3bbf61533ab643d927","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-03T07:13:43Z","title_canon_sha256":"cfa9409316379d81c269af3f59045f1cfd8a5b4bc10b72cd91ea5258b3fbc596"},"schema_version":"1.0","source":{"id":"1803.01118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01118","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01118v2","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01118","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"QW6OBNOLMFB4","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QW6OBNOLMFB4GXEF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QW6OBNOL","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:c9b58e9c7f26bf923c2f841c3ff58f2d7e99ca9755705719c588a5fe37196800","target":"graph","created_at":"2026-05-17T23:56:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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.","authors_text":"Bradly C. Stadie, Ge Yang, Ilya Sutskever, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-03T07:13:43Z","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01118","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2baea18120ae07e7e716035e60a8934fbb28ff9711665851460799f474161a0","target":"record","created_at":"2026-05-17T23:56:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"67567713d3af65d196af8878aa60d9334b23d48a31e0bc3bbf61533ab643d927","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-03T07:13:43Z","title_canon_sha256":"cfa9409316379d81c269af3f59045f1cfd8a5b4bc10b72cd91ea5258b3fbc596"},"schema_version":"1.0","source":{"id":"1803.01118","kind":"arxiv","version":2}},"canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","first_computed_at":"2026-05-17T23:56:29.955204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:29.955204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Kx52nQTDUWRb8PiL7dIQNqdCIrsLOTXTHPYXgZzdCFUKi5zKlzSBI9IQNe7r7JFL6mD9Cy5bvK/nm4/P+RhCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:29.955639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2baea18120ae07e7e716035e60a8934fbb28ff9711665851460799f474161a0","sha256:c9b58e9c7f26bf923c2f841c3ff58f2d7e99ca9755705719c588a5fe37196800"],"state_sha256":"09c60d20b8cc44849176c606a4317ef21e6eacb4b54fbe7be0982c540d86d20c"}