{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NIPJBPJDHL2XISJY7PYWYJAVZJ","short_pith_number":"pith:NIPJBPJD","canonical_record":{"source":{"id":"1905.06527","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T04:42:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d416a87741089c9271012ae76328107f3063b391c60c2c410192ca69fe52f05f","abstract_canon_sha256":"d02cb19bd085107b0bd2e0688ec7bc87b42b6caca6e4ae923137548a5a7cf555"},"schema_version":"1.0"},"canonical_sha256":"6a1e90bd233af5744938fbf16c2415ca5c95514e6a047f89d23a2ec8bb505801","source":{"kind":"arxiv","id":"1905.06527","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06527","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06527v3","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06527","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"NIPJBPJDHL2X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NIPJBPJDHL2XISJY","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NIPJBPJD","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NIPJBPJDHL2XISJY7PYWYJAVZJ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06527","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T04:42:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d416a87741089c9271012ae76328107f3063b391c60c2c410192ca69fe52f05f","abstract_canon_sha256":"d02cb19bd085107b0bd2e0688ec7bc87b42b6caca6e4ae923137548a5a7cf555"},"schema_version":"1.0"},"canonical_sha256":"6a1e90bd233af5744938fbf16c2415ca5c95514e6a047f89d23a2ec8bb505801","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:18.594562Z","signature_b64":"yT4t96pqAchX0VOa9U7KxK2iMPmrXOyaBk3GqhRaJ6r/PSNgs8HZ1EPX42F4RKsfg/RuYYZ64IxrxtknXlCMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a1e90bd233af5744938fbf16c2415ca5c95514e6a047f89d23a2ec8bb505801","last_reissued_at":"2026-05-17T23:44:18.593995Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:18.593995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06527","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgTMnBNX49Xy0cgEqlKErRbV5GwDdDUbvWoEy6QcaKMdp/gwxNZgdPSZKVCfK+1JqlvZz+Art0Ob7ipeP6xIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:23:05.609519Z"},"content_sha256":"844c34fc9a042df1ec15d4823cde93f11b0749b46763aade3ccf08313f6df17e","schema_version":"1.0","event_id":"sha256:844c34fc9a042df1ec15d4823cde93f11b0749b46763aade3ccf08313f6df17e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NIPJBPJDHL2XISJY7PYWYJAVZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Reinforcement Learning with Task Embedding and Shared Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin Lan, Pinghui Wang, Xiaohong Guan, Zhenguo Li","submitted_at":"2019-05-16T04:42:25Z","abstract_excerpt":"Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06527","kind":"arxiv","version":3},"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":"2026-05-17T23:44:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uK8IdH1C0XO8DVbDtZM5NLQZZiUS4t65/aOKAvliza2UAwBy6lWwZfn7nkTdK4e/0OS9KleLyB5OD72/3YCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:23:05.610219Z"},"content_sha256":"0fb106aca1abf88837063ae98c868273b6307cc3fc0b897aa71e2c36cf07432c","schema_version":"1.0","event_id":"sha256:0fb106aca1abf88837063ae98c868273b6307cc3fc0b897aa71e2c36cf07432c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/bundle.json","state_url":"https://pith.science/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/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":"2026-05-25T17:23:05Z","links":{"resolver":"https://pith.science/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ","bundle":"https://pith.science/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/bundle.json","state":"https://pith.science/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIPJBPJDHL2XISJY7PYWYJAVZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NIPJBPJDHL2XISJY7PYWYJAVZJ","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":"d02cb19bd085107b0bd2e0688ec7bc87b42b6caca6e4ae923137548a5a7cf555","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T04:42:25Z","title_canon_sha256":"d416a87741089c9271012ae76328107f3063b391c60c2c410192ca69fe52f05f"},"schema_version":"1.0","source":{"id":"1905.06527","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06527","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06527v3","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06527","created_at":"2026-05-17T23:44:18Z"},{"alias_kind":"pith_short_12","alias_value":"NIPJBPJDHL2X","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NIPJBPJDHL2XISJY","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NIPJBPJD","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:0fb106aca1abf88837063ae98c868273b6307cc3fc0b897aa71e2c36cf07432c","target":"graph","created_at":"2026-05-17T23:44:18Z","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":"Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose t","authors_text":"Lin Lan, Pinghui Wang, Xiaohong Guan, Zhenguo Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T04:42:25Z","title":"Meta Reinforcement Learning with Task Embedding and Shared Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06527","kind":"arxiv","version":3},"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":"sha256:844c34fc9a042df1ec15d4823cde93f11b0749b46763aade3ccf08313f6df17e","target":"record","created_at":"2026-05-17T23:44:18Z","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":"d02cb19bd085107b0bd2e0688ec7bc87b42b6caca6e4ae923137548a5a7cf555","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-16T04:42:25Z","title_canon_sha256":"d416a87741089c9271012ae76328107f3063b391c60c2c410192ca69fe52f05f"},"schema_version":"1.0","source":{"id":"1905.06527","kind":"arxiv","version":3}},"canonical_sha256":"6a1e90bd233af5744938fbf16c2415ca5c95514e6a047f89d23a2ec8bb505801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a1e90bd233af5744938fbf16c2415ca5c95514e6a047f89d23a2ec8bb505801","first_computed_at":"2026-05-17T23:44:18.593995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:18.593995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yT4t96pqAchX0VOa9U7KxK2iMPmrXOyaBk3GqhRaJ6r/PSNgs8HZ1EPX42F4RKsfg/RuYYZ64IxrxtknXlCMBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:18.594562Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06527","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:844c34fc9a042df1ec15d4823cde93f11b0749b46763aade3ccf08313f6df17e","sha256:0fb106aca1abf88837063ae98c868273b6307cc3fc0b897aa71e2c36cf07432c"],"state_sha256":"4053d79a80e583be76828023cfd059a5f494014ce8f52ceb8ef71e657bc9eab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIIrJLbYJz1Prl8ejos5KKTkAQrPb4LKcG9cpkduOuXoFuAmNtTK7PB/1h+DHdudxtEe0AMxCkxKCepVzVJ9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:23:05.614045Z","bundle_sha256":"67f197e76e3c804e8dcccb35bac407164fd0b792300f68d3a185b97a26271eb3"}}