{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BOTOITRL5YY52ASTQHB56I7AJX","short_pith_number":"pith:BOTOITRL","canonical_record":{"source":{"id":"2006.08170","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-15T06:56:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c4a45000df5a551ced60a6683a80a925d2c0df569ffb4b7f18760467b78b1ef0","abstract_canon_sha256":"8252e326d23a8e625b09bd2021fad39e3f049be1235ccbf770a901075aae1aa7"},"schema_version":"1.0"},"canonical_sha256":"0ba6e44e2bee31dd025381c3df23e04df7352203e2969b790ad7aa9ccad2a493","source":{"kind":"arxiv","id":"2006.08170","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08170","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08170v5","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08170","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"BOTOITRL5YY5","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_16","alias_value":"BOTOITRL5YY52AST","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_8","alias_value":"BOTOITRL","created_at":"2026-07-05T03:31:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BOTOITRL5YY52ASTQHB56I7AJX","target":"record","payload":{"canonical_record":{"source":{"id":"2006.08170","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-15T06:56:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c4a45000df5a551ced60a6683a80a925d2c0df569ffb4b7f18760467b78b1ef0","abstract_canon_sha256":"8252e326d23a8e625b09bd2021fad39e3f049be1235ccbf770a901075aae1aa7"},"schema_version":"1.0"},"canonical_sha256":"0ba6e44e2bee31dd025381c3df23e04df7352203e2969b790ad7aa9ccad2a493","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:01.794162Z","signature_b64":"99Ha+On0jNEv+17oHkqozODrfqh5Not+yj0nZPgAp+R+637vKMbpZ1He5RctyNg3qZpD40BRCBHIXdii0f5gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba6e44e2bee31dd025381c3df23e04df7352203e2969b790ad7aa9ccad2a493","last_reissued_at":"2026-07-05T03:31:01.793749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:01.793749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.08170","source_version":5,"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":"1aSEuUg4ybRZwRul2XsNiMLi6deaEEM6LolF6qh5dDVOEYexIGF69ZmDuWBsWgsJq9Ihbaca9Wf9+zYzQCyRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:25.098413Z"},"content_sha256":"2b5b4bb8e5bd7b6913573598f55fa3052b09c9e254b88e1e8a325018fe255a48","schema_version":"1.0","event_id":"sha256:2b5b4bb8e5bd7b6913573598f55fa3052b09c9e254b88e1e8a325018fe255a48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BOTOITRL5YY52ASTQHB56I7AJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Changjie Fan, Chongjie Zhang, Hao Hu, Jianhao Wang, Jin Zhang, Tong Chen, Yingfeng Chen","submitted_at":"2020-06-15T06:56:18Z","abstract_excerpt":"Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires quickly finding informative task-relevant experiences in both meta-training and adaptation. To address this challenge, we explicitly model an exploration policy learning problem for meta-RL, which is separated from exploitation policy learning, and introduce a novel empowerment-driven exploration objective, which aims to maximize information gain for task i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08170","kind":"arxiv","version":5},"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/2006.08170/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":"jZR7FTSJn0JZUQcJEcj3oYDmcw1iWunZ8lQrVTcJicwLtBR73OooxkCWEZDE3hrNcpBi/8rN05ic5sRNR9BbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:25.099033Z"},"content_sha256":"a8c78f3b90631514d5a64c56e2551b032201211275618c1fa6e97bd18afa239c","schema_version":"1.0","event_id":"sha256:a8c78f3b90631514d5a64c56e2551b032201211275618c1fa6e97bd18afa239c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOTOITRL5YY52ASTQHB56I7AJX/bundle.json","state_url":"https://pith.science/pith/BOTOITRL5YY52ASTQHB56I7AJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOTOITRL5YY52ASTQHB56I7AJX/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":"2026-07-07T01:59:25Z","links":{"resolver":"https://pith.science/pith/BOTOITRL5YY52ASTQHB56I7AJX","bundle":"https://pith.science/pith/BOTOITRL5YY52ASTQHB56I7AJX/bundle.json","state":"https://pith.science/pith/BOTOITRL5YY52ASTQHB56I7AJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOTOITRL5YY52ASTQHB56I7AJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BOTOITRL5YY52ASTQHB56I7AJX","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":"8252e326d23a8e625b09bd2021fad39e3f049be1235ccbf770a901075aae1aa7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-15T06:56:18Z","title_canon_sha256":"c4a45000df5a551ced60a6683a80a925d2c0df569ffb4b7f18760467b78b1ef0"},"schema_version":"1.0","source":{"id":"2006.08170","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.08170","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"2006.08170v5","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08170","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"BOTOITRL5YY5","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_16","alias_value":"BOTOITRL5YY52AST","created_at":"2026-07-05T03:31:01Z"},{"alias_kind":"pith_short_8","alias_value":"BOTOITRL","created_at":"2026-07-05T03:31:01Z"}],"graph_snapshots":[{"event_id":"sha256:a8c78f3b90631514d5a64c56e2551b032201211275618c1fa6e97bd18afa239c","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/2006.08170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires quickly finding informative task-relevant experiences in both meta-training and adaptation. To address this challenge, we explicitly model an exploration policy learning problem for meta-RL, which is separated from exploitation policy learning, and introduce a novel empowerment-driven exploration objective, which aims to maximize information gain for task i","authors_text":"Changjie Fan, Chongjie Zhang, Hao Hu, Jianhao Wang, Jin Zhang, Tong Chen, Yingfeng Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-15T06:56:18Z","title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08170","kind":"arxiv","version":5},"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":"sha256:2b5b4bb8e5bd7b6913573598f55fa3052b09c9e254b88e1e8a325018fe255a48","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":"8252e326d23a8e625b09bd2021fad39e3f049be1235ccbf770a901075aae1aa7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-15T06:56:18Z","title_canon_sha256":"c4a45000df5a551ced60a6683a80a925d2c0df569ffb4b7f18760467b78b1ef0"},"schema_version":"1.0","source":{"id":"2006.08170","kind":"arxiv","version":5}},"canonical_sha256":"0ba6e44e2bee31dd025381c3df23e04df7352203e2969b790ad7aa9ccad2a493","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ba6e44e2bee31dd025381c3df23e04df7352203e2969b790ad7aa9ccad2a493","first_computed_at":"2026-07-05T03:31:01.793749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:01.793749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"99Ha+On0jNEv+17oHkqozODrfqh5Not+yj0nZPgAp+R+637vKMbpZ1He5RctyNg3qZpD40BRCBHIXdii0f5gDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:01.794162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.08170","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b5b4bb8e5bd7b6913573598f55fa3052b09c9e254b88e1e8a325018fe255a48","sha256:a8c78f3b90631514d5a64c56e2551b032201211275618c1fa6e97bd18afa239c"],"state_sha256":"0330be926db585412c044328381a22b5a7123fcb28a2c150c4355b9969189469"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSM4DIzlgzMII6fVyZAvvq3BqAGFL2zLX0ueGGlLtd+b4BH48N7UylniYc4mHwB35ZfzY71bPUj6o0a+GXiNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T01:59:25.102488Z","bundle_sha256":"2c4fe26a9ce5f956278c8296ca48471129c0292e8b168f2c3c4e00d73a609675"}}