{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B7FTF4IJB4DDA6HJMRDCKAL6YV","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":"35a2e57c1ac4726b5e7ad96a05387ff7f0d145306e28b41cec63e853aa9f634a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T18:12:26Z","title_canon_sha256":"80e286dbea28d7a351dd520594f1ebd01eee6feaed758d7cca6ffdabce5aed49"},"schema_version":"1.0","source":{"id":"2106.01404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01404","created_at":"2026-07-05T02:45:51Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01404v1","created_at":"2026-07-05T02:45:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01404","created_at":"2026-07-05T02:45:51Z"},{"alias_kind":"pith_short_12","alias_value":"B7FTF4IJB4DD","created_at":"2026-07-05T02:45:51Z"},{"alias_kind":"pith_short_16","alias_value":"B7FTF4IJB4DDA6HJ","created_at":"2026-07-05T02:45:51Z"},{"alias_kind":"pith_short_8","alias_value":"B7FTF4IJ","created_at":"2026-07-05T02:45:51Z"}],"graph_snapshots":[{"event_id":"sha256:7bb286391996b200f40cb6af67c2f9b33952eb65170d94715d88bd118cf8c41e","target":"graph","created_at":"2026-07-05T02:45:51Z","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/2106.01404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to reach goal states and learning diverse skills through mutual information (MI) maximization have been proposed as principled frameworks for self-supervised reinforcement learning, allowing agents to acquire broadly applicable multitask policies with minimal reward engineering. Starting from a simple observation that the standard goal-conditioned RL (GCRL) is encapsulated by the optimization objective of variational empowerment, we discuss how GCRL and MI-based RL can be generalized into a single family of methods, which we name variational GCRL (VGCRL), interpreting variational MI m","authors_text":"Archit Sharma, Honglak Lee, Jongwook Choi, Sergey Levine, Shixiang Shane Gu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T18:12:26Z","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01404","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":"sha256:6aa1cc9da404f40b8dc8577a3d38742bf08bdfeb89827c14ee047039e835c800","target":"record","created_at":"2026-07-05T02:45:51Z","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":"35a2e57c1ac4726b5e7ad96a05387ff7f0d145306e28b41cec63e853aa9f634a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T18:12:26Z","title_canon_sha256":"80e286dbea28d7a351dd520594f1ebd01eee6feaed758d7cca6ffdabce5aed49"},"schema_version":"1.0","source":{"id":"2106.01404","kind":"arxiv","version":1}},"canonical_sha256":"0fcb32f1090f063078e9644625017ec56533540b2fe6c758fcc92bd3e01a8d10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fcb32f1090f063078e9644625017ec56533540b2fe6c758fcc92bd3e01a8d10","first_computed_at":"2026-07-05T02:45:51.004019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:51.004019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZemJP4H+YD2eFF7k/5TMSb0Fk6Uw+hIBSMIZW+NERT1gs3obdxyGB/GRkXnK0vT1CCd9lUIWtjDSEKkeO+1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:51.004616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aa1cc9da404f40b8dc8577a3d38742bf08bdfeb89827c14ee047039e835c800","sha256:7bb286391996b200f40cb6af67c2f9b33952eb65170d94715d88bd118cf8c41e"],"state_sha256":"ef2ef786e938cc6e751be9cd7e9b62810631d7fc51760e6af9ef6a321a4201b3"}