{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QW6OBNOLMFB4GXEFCSSXLLR7N4","short_pith_number":"pith:QW6OBNOL","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"},"canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","source":{"kind":"arxiv","id":"1803.01118","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QW6OBNOLMFB4GXEFCSSXLLR7N4","target":"record","payload":{"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"},"canonical_sha256":"85bce0b5cb6143c35c8514a575ae3f6f28bd2f79b13ae431318425aee00d8542","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"},"source_kind":"arxiv","source_id":"1803.01118","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NVBuzwsrzRwBaYxHbU4TReuTLLx7Uf8P0ycZH483VsCuf8xVLQFWQHJZcomifJWPHP4gHx+r95JO5r3Yx5eECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:10:38.402902Z"},"content_sha256":"d2baea18120ae07e7e716035e60a8934fbb28ff9711665851460799f474161a0","schema_version":"1.0","event_id":"sha256:d2baea18120ae07e7e716035e60a8934fbb28ff9711665851460799f474161a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QW6OBNOLMFB4GXEFCSSXLLR7N4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgkvytOGauhQSNTrC7clGT3XkjBsVQkpDfY8TZehQfsx9mO4EcaQSLMxcBS1fn1pMgtBETIKZeEMf5B8XNp+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T08:10:38.403498Z"},"content_sha256":"c9b58e9c7f26bf923c2f841c3ff58f2d7e99ca9755705719c588a5fe37196800","schema_version":"1.0","event_id":"sha256:c9b58e9c7f26bf923c2f841c3ff58f2d7e99ca9755705719c588a5fe37196800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/bundle.json","state_url":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T08:10:38Z","links":{"resolver":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4","bundle":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/bundle.json","state":"https://pith.science/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QW6OBNOLMFB4GXEFCSSXLLR7N4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzBS3JN9pZ9Q0vKurQ+/fISD/z3Zz9Y14T5gmMxcJxnWdVo6ffjzjPRfKI60QDzltPk+qUeGksasy5ncdCBeAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T08:10:38.406168Z","bundle_sha256":"1f256682dbff121b0dcf191ab7960fe541e40b7967ce0170d160a1e27dfa068e"}}