{"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"}