{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TJK757JLMJAJ5G4XQ23BKKURET","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":"3552f31c311bf56fd7587d81a231e9fc16a8f0b3631d7f4a89b29661caf636a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T15:45:17Z","title_canon_sha256":"d23cb987306caaf9c72d19eab787688a60e7b6a78d14db5b77fe745027629351"},"schema_version":"1.0","source":{"id":"2102.09430","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09430","created_at":"2026-07-05T02:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09430v4","created_at":"2026-07-05T02:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09430","created_at":"2026-07-05T02:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"TJK757JLMJAJ","created_at":"2026-07-05T02:50:44Z"},{"alias_kind":"pith_short_16","alias_value":"TJK757JLMJAJ5G4X","created_at":"2026-07-05T02:50:44Z"},{"alias_kind":"pith_short_8","alias_value":"TJK757JL","created_at":"2026-07-05T02:50:44Z"}],"graph_snapshots":[{"event_id":"sha256:67765a6b7d1b6933c692f9533b3da75ada1afd60d36c5523a9b6b466ffdd270d","target":"graph","created_at":"2026-07-05T02:50:44Z","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/2102.09430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observation spaces still remains a challenge. This paper presents Random Encoders for Efficient Exploration (RE3), an exploration method that utilizes state entropy as an intrinsic reward. In order to estimate state entropy in environments with high-dimensional observations, we utilize a k-nearest neighbor entropy estimator in the low-dimensional representation space of a convolutional encoder. In particular, we find that ","authors_text":"Honglak Lee, Jinwoo Shin, Kimin Lee, Lili Chen, Pieter Abbeel, Younggyo Seo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T15:45:17Z","title":"State Entropy Maximization with Random Encoders for Efficient Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09430","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":"sha256:8e823cf409bfc7d8be5add54e65690eff88f27ca063d8df64a2c000f101710e7","target":"record","created_at":"2026-07-05T02:50:44Z","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":"3552f31c311bf56fd7587d81a231e9fc16a8f0b3631d7f4a89b29661caf636a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T15:45:17Z","title_canon_sha256":"d23cb987306caaf9c72d19eab787688a60e7b6a78d14db5b77fe745027629351"},"schema_version":"1.0","source":{"id":"2102.09430","kind":"arxiv","version":4}},"canonical_sha256":"9a55fefd2b62409e9b9786b6152a9124dae8e10199a122224cf50c50a15e6be0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a55fefd2b62409e9b9786b6152a9124dae8e10199a122224cf50c50a15e6be0","first_computed_at":"2026-07-05T02:50:44.205626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:44.205626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LH461zLknUGbv460xyU5f7mlRRzHnT+Y+IXk/v2uTD9vK+Ss4MDg7cR7nY5PkKpBe3L66h5TNU7+KRsiK/jEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:44.206140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09430","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e823cf409bfc7d8be5add54e65690eff88f27ca063d8df64a2c000f101710e7","sha256:67765a6b7d1b6933c692f9533b3da75ada1afd60d36c5523a9b6b466ffdd270d"],"state_sha256":"c4de48d31e48059d3b8db43acdb8ca3898ef7fd8e8813fccefe20e4f74c392cf"}