{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XDP2LDEXCEZYLDNU7PIRJ5P3BN","short_pith_number":"pith:XDP2LDEX","schema_version":"1.0","canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","source":{"kind":"arxiv","id":"1802.04564","version":2},"attestation_state":"computed","paper":{"title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","submitted_at":"2018-02-13T11:18:41Z","abstract_excerpt":"Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and on-policy reinforcement learning algorithms. We show that by simply adding a distance measure to the loss function, the proposed methodology significantly enhances an agent's exploratory behaviors, and thus preventing the policy from being trapped in local optima. We further propo"},"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":"1802.04564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-13T11:18:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"69cd27019c4a1c5d4aa9f65fad00ca95e4625c4b20d291fb1dd63af2b53840f6","abstract_canon_sha256":"d9aa7db70a6d5bcd8986cf23cd81f638440f5029a68200c295f5408f7a82c5de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:12.918149Z","signature_b64":"apbUFcUZrq7cfDpSgxv3OUTj4N46oiPtfPLzrmgM8Pd4KBEKjimvF84wYtqAY2Tt7CVVy0OkUeWws71OkO1aCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","last_reissued_at":"2026-05-18T00:02:12.917431Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:12.917431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.AI","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","submitted_at":"2018-02-13T11:18:41Z","abstract_excerpt":"Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and on-policy reinforcement learning algorithms. We show that by simply adding a distance measure to the loss function, the proposed methodology significantly enhances an agent's exploratory behaviors, and thus preventing the policy from being trapped in local optima. We further propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04564","kind":"arxiv","version":2},"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":"1802.04564","created_at":"2026-05-18T00:02:12.917552+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04564v2","created_at":"2026-05-18T00:02:12.917552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04564","created_at":"2026-05-18T00:02:12.917552+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDP2LDEXCEZY","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDP2LDEXCEZYLDNU","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDP2LDEX","created_at":"2026-05-18T12:33:01.666342+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/XDP2LDEXCEZYLDNU7PIRJ5P3BN","json":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN.json","graph_json":"https://pith.science/api/pith-number/XDP2LDEXCEZYLDNU7PIRJ5P3BN/graph.json","events_json":"https://pith.science/api/pith-number/XDP2LDEXCEZYLDNU7PIRJ5P3BN/events.json","paper":"https://pith.science/paper/XDP2LDEX"},"agent_actions":{"view_html":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN","download_json":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN.json","view_paper":"https://pith.science/paper/XDP2LDEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04564&json=true","fetch_graph":"https://pith.science/api/pith-number/XDP2LDEXCEZYLDNU7PIRJ5P3BN/graph.json","fetch_events":"https://pith.science/api/pith-number/XDP2LDEXCEZYLDNU7PIRJ5P3BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/action/storage_attestation","attest_author":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/action/author_attestation","sign_citation":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/action/citation_signature","submit_replication":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/action/replication_record"}},"created_at":"2026-05-18T00:02:12.917552+00:00","updated_at":"2026-05-18T00:02:12.917552+00:00"}