{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EMCBRL4KI4CCEOV25QAHO3AEV5","short_pith_number":"pith:EMCBRL4K","canonical_record":{"source":{"id":"1702.07490","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-24T08:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"a9b4f6a7cc97aa2297bafca0132ce03ba07b52182f97cd26c946e9b5bb972cea","abstract_canon_sha256":"71b8537626947410e12700a8e2dc07b1278f048681ef0f3801a8ac1d3b6d0f10"},"schema_version":"1.0"},"canonical_sha256":"230418af8a4704223abaec00776c04af64f741102350789b6bafaee840e92416","source":{"kind":"arxiv","id":"1702.07490","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07490","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07490v1","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07490","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"EMCBRL4KI4CC","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EMCBRL4KI4CCEOV2","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EMCBRL4K","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EMCBRL4KI4CCEOV25QAHO3AEV5","target":"record","payload":{"canonical_record":{"source":{"id":"1702.07490","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-24T08:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"a9b4f6a7cc97aa2297bafca0132ce03ba07b52182f97cd26c946e9b5bb972cea","abstract_canon_sha256":"71b8537626947410e12700a8e2dc07b1278f048681ef0f3801a8ac1d3b6d0f10"},"schema_version":"1.0"},"canonical_sha256":"230418af8a4704223abaec00776c04af64f741102350789b6bafaee840e92416","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:03.178250Z","signature_b64":"HAppf2W6H8OtHwSoU+klDhgexigTxscrDHBZuVseQ28D1e599llrEVvTTDOPrbsz8oORIdjQVjUEE7e2m4UpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"230418af8a4704223abaec00776c04af64f741102350789b6bafaee840e92416","last_reissued_at":"2026-05-18T00:50:03.177687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:03.177687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.07490","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nS5M1Iy+4Ohlu8XWE/S7nithbVx0ZpW8Ibt80lXMINueBoejfKvGhUdxB0Cj+Tp30/wwS1wefsDH+0PVZFK+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:30:28.129048Z"},"content_sha256":"eba708b76870f26335a9abacdb7e16c14e12569316b2d16719aefab20f24ad37","schema_version":"1.0","event_id":"sha256:eba708b76870f26335a9abacdb7e16c14e12569316b2d16719aefab20f24ad37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EMCBRL4KI4CCEOV25QAHO3AEV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Meta-learning by Parallel Algorithm Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Kenji Doya, Stefan Elfwing","submitted_at":"2017-02-24T08:25:23Z","abstract_excerpt":"The efficiency of reinforcement learning algorithms depends critically on a few meta-parameters that modulates the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question in reinforcement learning, which arguably has become more of an issue recently with the success of deep reinforcement learning in high-dimensional state spaces. The long learning times in domains such as Atari 2600 video games makes it not feasible to perform comprehensive searches of appropriate meta-parameter values. We propose the Online Meta-learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07490","kind":"arxiv","version":1},"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":"2026-05-18T00:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbRTu9xWXtIIIEV2h+BXORcmoGArnK424EIHrPfhiXaPDFJ5iA+6psn/qG46gERSWYZvARZWhEsSW2pzY/HBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T23:30:28.129583Z"},"content_sha256":"996adb1352d0b6469316c385d8ec30d6722162c238919ac955881f80bd29d199","schema_version":"1.0","event_id":"sha256:996adb1352d0b6469316c385d8ec30d6722162c238919ac955881f80bd29d199"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/bundle.json","state_url":"https://pith.science/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/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":"2026-06-08T23:30:28Z","links":{"resolver":"https://pith.science/pith/EMCBRL4KI4CCEOV25QAHO3AEV5","bundle":"https://pith.science/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/bundle.json","state":"https://pith.science/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMCBRL4KI4CCEOV25QAHO3AEV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EMCBRL4KI4CCEOV25QAHO3AEV5","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":"71b8537626947410e12700a8e2dc07b1278f048681ef0f3801a8ac1d3b6d0f10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-24T08:25:23Z","title_canon_sha256":"a9b4f6a7cc97aa2297bafca0132ce03ba07b52182f97cd26c946e9b5bb972cea"},"schema_version":"1.0","source":{"id":"1702.07490","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.07490","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"1702.07490v1","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07490","created_at":"2026-05-18T00:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"EMCBRL4KI4CC","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EMCBRL4KI4CCEOV2","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EMCBRL4K","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:996adb1352d0b6469316c385d8ec30d6722162c238919ac955881f80bd29d199","target":"graph","created_at":"2026-05-18T00:50:03Z","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":"The efficiency of reinforcement learning algorithms depends critically on a few meta-parameters that modulates the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question in reinforcement learning, which arguably has become more of an issue recently with the success of deep reinforcement learning in high-dimensional state spaces. The long learning times in domains such as Atari 2600 video games makes it not feasible to perform comprehensive searches of appropriate meta-parameter values. We propose the Online Meta-learni","authors_text":"Eiji Uchibe, Kenji Doya, Stefan Elfwing","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-24T08:25:23Z","title":"Online Meta-learning by Parallel Algorithm Competition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07490","kind":"arxiv","version":1},"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:eba708b76870f26335a9abacdb7e16c14e12569316b2d16719aefab20f24ad37","target":"record","created_at":"2026-05-18T00:50:03Z","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":"71b8537626947410e12700a8e2dc07b1278f048681ef0f3801a8ac1d3b6d0f10","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-24T08:25:23Z","title_canon_sha256":"a9b4f6a7cc97aa2297bafca0132ce03ba07b52182f97cd26c946e9b5bb972cea"},"schema_version":"1.0","source":{"id":"1702.07490","kind":"arxiv","version":1}},"canonical_sha256":"230418af8a4704223abaec00776c04af64f741102350789b6bafaee840e92416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"230418af8a4704223abaec00776c04af64f741102350789b6bafaee840e92416","first_computed_at":"2026-05-18T00:50:03.177687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:03.177687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAppf2W6H8OtHwSoU+klDhgexigTxscrDHBZuVseQ28D1e599llrEVvTTDOPrbsz8oORIdjQVjUEE7e2m4UpAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:03.178250Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.07490","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eba708b76870f26335a9abacdb7e16c14e12569316b2d16719aefab20f24ad37","sha256:996adb1352d0b6469316c385d8ec30d6722162c238919ac955881f80bd29d199"],"state_sha256":"13e45952da9d4f66fdcc769121d3fa74be753ea6b097240238a318ce90a0b5a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFBqEvWVhkR08dr26XtIpYXfGUa2GpBWOULeu+VeAd+aKQKfBxh3Gu6kNFMyhmImLgnQLlo9cbybl7eoiRPYCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T23:30:28.132029Z","bundle_sha256":"c9d903d04c84eafdb5db3a54e083f9778b9e45d0dd9d9dd98f01d4730c8c355d"}}