{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:525PJ4D7MCHERV65DLDC4HZZOQ","short_pith_number":"pith:525PJ4D7","canonical_record":{"source":{"id":"2008.02790","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T17:57:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3c3dfd0264d28fca8cac48c19176be8ecb6e56da0afd94124d0cf291170cfd56","abstract_canon_sha256":"3a1838c3db8e2241d30215132353b517dd489b10dd01dd5bfebf90b42debe443"},"schema_version":"1.0"},"canonical_sha256":"eebaf4f07f608e48d7dd1ac62e1f39743090b5b20b178f29f2960d4337c61e99","source":{"kind":"arxiv","id":"2008.02790","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02790","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02790v4","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02790","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"525PJ4D7MCHE","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_16","alias_value":"525PJ4D7MCHERV65","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_8","alias_value":"525PJ4D7","created_at":"2026-07-05T03:31:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:525PJ4D7MCHERV65DLDC4HZZOQ","target":"record","payload":{"canonical_record":{"source":{"id":"2008.02790","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T17:57:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3c3dfd0264d28fca8cac48c19176be8ecb6e56da0afd94124d0cf291170cfd56","abstract_canon_sha256":"3a1838c3db8e2241d30215132353b517dd489b10dd01dd5bfebf90b42debe443"},"schema_version":"1.0"},"canonical_sha256":"eebaf4f07f608e48d7dd1ac62e1f39743090b5b20b178f29f2960d4337c61e99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:01.855622Z","signature_b64":"YnChdhYNq+6bskF26hMFzg5438tnrE8ShmCKFgsBirDfCp/lMtwSu1CHOqvI2erNBE3sD1BXgPHUWMnUkwvGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eebaf4f07f608e48d7dd1ac62e1f39743090b5b20b178f29f2960d4337c61e99","last_reissued_at":"2026-07-05T03:31:01.855213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:01.855213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.02790","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:31:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVwTow5UuROFfrLB4r2lzGcs4K7X20ov6CPXDuFoaU6CcpYegTBm99phfKkN6j2XlwAKMe6JThY3Yatv2KjfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:24:02.468426Z"},"content_sha256":"4ef4152c550b3640af7cf4d4b540e2730492c741d8cd63f8269b79c821587941","schema_version":"1.0","event_id":"sha256:4ef4152c550b3640af7cf4d4b540e2730492c741d8cd63f8269b79c821587941"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:525PJ4D7MCHERV65DLDC4HZZOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, Chelsea Finn, Evan Zheran Liu, Percy Liang","submitted_at":"2020-08-06T17:57:36Z","abstract_excerpt":"The goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and exploiting this information to solve the task. In principle, optimal exploration and exploitation can be learned end-to-end by simply maximizing task performance. However, such meta-RL approaches struggle with local optima due to a chicken-and-egg problem: learning to explore requires good exploitation to gauge the exploration's utility, but learning to exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02790","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.02790/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:31:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"exO3KpBvKo1k7PXoBsXTY9L4TW5nWqjfHuBHvDU0X1/ZeGxwNFdOdltjxrpNbSgKvnz8/cJ4xP3T2Yk3Ny9xBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:24:02.469043Z"},"content_sha256":"6a807a84cf1d4b44d8c6c73bd0dbaaa67b0549574bccf9d58dc67d24b9be1024","schema_version":"1.0","event_id":"sha256:6a807a84cf1d4b44d8c6c73bd0dbaaa67b0549574bccf9d58dc67d24b9be1024"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/525PJ4D7MCHERV65DLDC4HZZOQ/bundle.json","state_url":"https://pith.science/pith/525PJ4D7MCHERV65DLDC4HZZOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/525PJ4D7MCHERV65DLDC4HZZOQ/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":"2026-08-09T17:24:02Z","links":{"resolver":"https://pith.science/pith/525PJ4D7MCHERV65DLDC4HZZOQ","bundle":"https://pith.science/pith/525PJ4D7MCHERV65DLDC4HZZOQ/bundle.json","state":"https://pith.science/pith/525PJ4D7MCHERV65DLDC4HZZOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/525PJ4D7MCHERV65DLDC4HZZOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:525PJ4D7MCHERV65DLDC4HZZOQ","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":"3a1838c3db8e2241d30215132353b517dd489b10dd01dd5bfebf90b42debe443","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T17:57:36Z","title_canon_sha256":"3c3dfd0264d28fca8cac48c19176be8ecb6e56da0afd94124d0cf291170cfd56"},"schema_version":"1.0","source":{"id":"2008.02790","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02790","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02790v4","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02790","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"525PJ4D7MCHE","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_16","alias_value":"525PJ4D7MCHERV65","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_8","alias_value":"525PJ4D7","created_at":"2026-07-05T03:31:01Z"}],"graph_snapshots":[{"event_id":"sha256:6a807a84cf1d4b44d8c6c73bd0dbaaa67b0549574bccf9d58dc67d24b9be1024","target":"graph","created_at":"2026-07-05T03:31:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.02790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and exploiting this information to solve the task. In principle, optimal exploration and exploitation can be learned end-to-end by simply maximizing task performance. However, such meta-RL approaches struggle with local optima due to a chicken-and-egg problem: learning to explore requires good exploitation to gauge the exploration's utility, but learning to exp","authors_text":"Aditi Raghunathan, Chelsea Finn, Evan Zheran Liu, Percy Liang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T17:57:36Z","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02790","kind":"arxiv","version":4},"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":"sha256:4ef4152c550b3640af7cf4d4b540e2730492c741d8cd63f8269b79c821587941","target":"record","created_at":"2026-07-05T03:31:01Z","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":"3a1838c3db8e2241d30215132353b517dd489b10dd01dd5bfebf90b42debe443","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T17:57:36Z","title_canon_sha256":"3c3dfd0264d28fca8cac48c19176be8ecb6e56da0afd94124d0cf291170cfd56"},"schema_version":"1.0","source":{"id":"2008.02790","kind":"arxiv","version":4}},"canonical_sha256":"eebaf4f07f608e48d7dd1ac62e1f39743090b5b20b178f29f2960d4337c61e99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eebaf4f07f608e48d7dd1ac62e1f39743090b5b20b178f29f2960d4337c61e99","first_computed_at":"2026-07-05T03:31:01.855213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:01.855213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YnChdhYNq+6bskF26hMFzg5438tnrE8ShmCKFgsBirDfCp/lMtwSu1CHOqvI2erNBE3sD1BXgPHUWMnUkwvGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:01.855622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02790","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ef4152c550b3640af7cf4d4b540e2730492c741d8cd63f8269b79c821587941","sha256:6a807a84cf1d4b44d8c6c73bd0dbaaa67b0549574bccf9d58dc67d24b9be1024"],"state_sha256":"a471f09262ffaa5167281c55b4b1d85ded264c2e92d49481d10c8b2dfd878357"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7XqODX1jUAjNuuwHq+KixvUAhUTo4u1mb4AMG0dlw/Lj+U7RDPO8ugY3C8WLkgzrHVAEU0pmSWqRix9ZZFrCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:24:02.473003Z","bundle_sha256":"6ca43582262305b170fa31b18a728f6ece91776c0a54b8842f8a96d7e3a6ad4a"}}