{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TJK757JLMJAJ5G4XQ23BKKURET","short_pith_number":"pith:TJK757JL","schema_version":"1.0","canonical_sha256":"9a55fefd2b62409e9b9786b6152a9124dae8e10199a122224cf50c50a15e6be0","source":{"kind":"arxiv","id":"2102.09430","version":4},"attestation_state":"computed","paper":{"title":"State Entropy Maximization with Random Encoders for Efficient Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Jinwoo Shin, Kimin Lee, Lili Chen, Pieter Abbeel, Younggyo Seo","submitted_at":"2021-02-18T15:45:17Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.09430","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T15:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"d23cb987306caaf9c72d19eab787688a60e7b6a78d14db5b77fe745027629351","abstract_canon_sha256":"3552f31c311bf56fd7587d81a231e9fc16a8f0b3631d7f4a89b29661caf636a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:44.206140Z","signature_b64":"LH461zLknUGbv460xyU5f7mlRRzHnT+Y+IXk/v2uTD9vK+Ss4MDg7cR7nY5PkKpBe3L66h5TNU7+KRsiK/jEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a55fefd2b62409e9b9786b6152a9124dae8e10199a122224cf50c50a15e6be0","last_reissued_at":"2026-07-05T02:50:44.205626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:44.205626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State Entropy Maximization with Random Encoders for Efficient Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Jinwoo Shin, Kimin Lee, Lili Chen, Pieter Abbeel, Younggyo Seo","submitted_at":"2021-02-18T15:45:17Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09430","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/2102.09430/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.09430","created_at":"2026-07-05T02:50:44.205698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09430v4","created_at":"2026-07-05T02:50:44.205698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09430","created_at":"2026-07-05T02:50:44.205698+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJK757JLMJAJ","created_at":"2026-07-05T02:50:44.205698+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJK757JLMJAJ5G4X","created_at":"2026-07-05T02:50:44.205698+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJK757JL","created_at":"2026-07-05T02:50:44.205698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25424","citing_title":"Polychromic Objectives for Reinforcement Learning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET","json":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET.json","graph_json":"https://pith.science/api/pith-number/TJK757JLMJAJ5G4XQ23BKKURET/graph.json","events_json":"https://pith.science/api/pith-number/TJK757JLMJAJ5G4XQ23BKKURET/events.json","paper":"https://pith.science/paper/TJK757JL"},"agent_actions":{"view_html":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET","download_json":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET.json","view_paper":"https://pith.science/paper/TJK757JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09430&json=true","fetch_graph":"https://pith.science/api/pith-number/TJK757JLMJAJ5G4XQ23BKKURET/graph.json","fetch_events":"https://pith.science/api/pith-number/TJK757JLMJAJ5G4XQ23BKKURET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET/action/storage_attestation","attest_author":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET/action/author_attestation","sign_citation":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET/action/citation_signature","submit_replication":"https://pith.science/pith/TJK757JLMJAJ5G4XQ23BKKURET/action/replication_record"}},"created_at":"2026-07-05T02:50:44.205698+00:00","updated_at":"2026-07-05T02:50:44.205698+00:00"}