{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RX4MKH7Q63XHJKXOYVLAUVEBB2","short_pith_number":"pith:RX4MKH7Q","schema_version":"1.0","canonical_sha256":"8df8c51ff0f6ee74aaeec5560a54810e917c2727f901bf89c8d79e8f359129c5","source":{"kind":"arxiv","id":"1810.01176","version":6},"attestation_state":"computed","paper":{"title":"EMI: Exploration with Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"HyoungSeok Kim, Hyun Oh Song, Jaekyeom Kim, Sergey Levine, Yeonwoo Jeong","submitted_at":"2018-10-02T11:33:57Z","abstract_excerpt":"Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or discriminative modeling of novelty. We propose EMI, which is an exploration method that constructs embedding representation of states and actions that does not rely on generative decoding of the full observation but extracts predictive signals that can be used to guide exploratio"},"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":"1810.01176","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T11:33:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"38f5106be0b5c5cd438d60722618d19b5bee9c49f78d18276cd4832e7ed94074","abstract_canon_sha256":"1dcef7dc516ddef17c9bc619fa2d67ce0340180b666d758b513b44d0bf4ac923"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:28.236731Z","signature_b64":"mMaU/YWEiSyvtvXDnXZchhe06ujMQCUKN2NDezZogI5q+gEbujDibSVopQ3E9gFqXOi3Rfh8vWQAKpXJHU8xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8df8c51ff0f6ee74aaeec5560a54810e917c2727f901bf89c8d79e8f359129c5","last_reissued_at":"2026-05-17T23:43:28.236266Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:28.236266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMI: Exploration with Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"HyoungSeok Kim, Hyun Oh Song, Jaekyeom Kim, Sergey Levine, Yeonwoo Jeong","submitted_at":"2018-10-02T11:33:57Z","abstract_excerpt":"Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or discriminative modeling of novelty. We propose EMI, which is an exploration method that constructs embedding representation of states and actions that does not rely on generative decoding of the full observation but extracts predictive signals that can be used to guide exploratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01176","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1810.01176","created_at":"2026-05-17T23:43:28.236346+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01176v6","created_at":"2026-05-17T23:43:28.236346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01176","created_at":"2026-05-17T23:43:28.236346+00:00"},{"alias_kind":"pith_short_12","alias_value":"RX4MKH7Q63XH","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RX4MKH7Q63XHJKXO","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RX4MKH7Q","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2","json":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2.json","graph_json":"https://pith.science/api/pith-number/RX4MKH7Q63XHJKXOYVLAUVEBB2/graph.json","events_json":"https://pith.science/api/pith-number/RX4MKH7Q63XHJKXOYVLAUVEBB2/events.json","paper":"https://pith.science/paper/RX4MKH7Q"},"agent_actions":{"view_html":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2","download_json":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2.json","view_paper":"https://pith.science/paper/RX4MKH7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01176&json=true","fetch_graph":"https://pith.science/api/pith-number/RX4MKH7Q63XHJKXOYVLAUVEBB2/graph.json","fetch_events":"https://pith.science/api/pith-number/RX4MKH7Q63XHJKXOYVLAUVEBB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2/action/storage_attestation","attest_author":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2/action/author_attestation","sign_citation":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2/action/citation_signature","submit_replication":"https://pith.science/pith/RX4MKH7Q63XHJKXOYVLAUVEBB2/action/replication_record"}},"created_at":"2026-05-17T23:43:28.236346+00:00","updated_at":"2026-05-17T23:43:28.236346+00:00"}