{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XDP2LDEXCEZYLDNU7PIRJ5P3BN","short_pith_number":"pith:XDP2LDEX","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"},"canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","source":{"kind":"arxiv","id":"1802.04564","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04564","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04564v2","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04564","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"XDP2LDEXCEZY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XDP2LDEXCEZYLDNU","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XDP2LDEX","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XDP2LDEXCEZYLDNU7PIRJ5P3BN","target":"record","payload":{"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"},"canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","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"},"source_kind":"arxiv","source_id":"1802.04564","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oE6o5NZPTTDIhuCpxQsZ+ih0lpFfmBSG175S5CikR16nl2XxYI6PV1eV1fjhmWtKd7PmyYvTElMNS84svC+VBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:43:26.237970Z"},"content_sha256":"1c2847d5fe8ba7bede420bc025b5c976bbf033d5060f06db31b8e277f3668679","schema_version":"1.0","event_id":"sha256:1c2847d5fe8ba7bede420bc025b5c976bbf033d5060f06db31b8e277f3668679"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XDP2LDEXCEZYLDNU7PIRJ5P3BN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ZEmD2mG4Y80Gmuw1+15Fmij/4lD3a7vz3Bo8n7lCRyLn1K/VG174uIYCJHjHllUJal7AFRMwbgnxds9x+9iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:43:26.238331Z"},"content_sha256":"65e0fba20aab244dd9fe5ab90b6658dc4cd7e29d2489602f475573d9260e0e11","schema_version":"1.0","event_id":"sha256:65e0fba20aab244dd9fe5ab90b6658dc4cd7e29d2489602f475573d9260e0e11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/bundle.json","state_url":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T21:43:26Z","links":{"resolver":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN","bundle":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/bundle.json","state":"https://pith.science/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XDP2LDEXCEZYLDNU7PIRJ5P3BN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XDP2LDEXCEZYLDNU7PIRJ5P3BN","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":"d9aa7db70a6d5bcd8986cf23cd81f638440f5029a68200c295f5408f7a82c5de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-13T11:18:41Z","title_canon_sha256":"69cd27019c4a1c5d4aa9f65fad00ca95e4625c4b20d291fb1dd63af2b53840f6"},"schema_version":"1.0","source":{"id":"1802.04564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04564","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04564v2","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04564","created_at":"2026-05-18T00:02:12Z"},{"alias_kind":"pith_short_12","alias_value":"XDP2LDEXCEZY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XDP2LDEXCEZYLDNU","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XDP2LDEX","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:65e0fba20aab244dd9fe5ab90b6658dc4cd7e29d2489602f475573d9260e0e11","target":"graph","created_at":"2026-05-18T00:02:12Z","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"},"paper":{"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","authors_text":"Chun-Yi Lee, Shih-Yang Su, Tzu-Yun Shann, Yi-Hsiang Chang, Zhang-Wei Hong","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-13T11:18:41Z","title":"Diversity-Driven Exploration Strategy for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04564","kind":"arxiv","version":2},"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":"sha256:1c2847d5fe8ba7bede420bc025b5c976bbf033d5060f06db31b8e277f3668679","target":"record","created_at":"2026-05-18T00:02:12Z","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":"d9aa7db70a6d5bcd8986cf23cd81f638440f5029a68200c295f5408f7a82c5de","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-13T11:18:41Z","title_canon_sha256":"69cd27019c4a1c5d4aa9f65fad00ca95e4625c4b20d291fb1dd63af2b53840f6"},"schema_version":"1.0","source":{"id":"1802.04564","kind":"arxiv","version":2}},"canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8dfa58c971133858db4fbd114f5fb0b44263d7f54b7e7cb14a2652f75225700","first_computed_at":"2026-05-18T00:02:12.917431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:12.917431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"apbUFcUZrq7cfDpSgxv3OUTj4N46oiPtfPLzrmgM8Pd4KBEKjimvF84wYtqAY2Tt7CVVy0OkUeWws71OkO1aCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:12.918149Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c2847d5fe8ba7bede420bc025b5c976bbf033d5060f06db31b8e277f3668679","sha256:65e0fba20aab244dd9fe5ab90b6658dc4cd7e29d2489602f475573d9260e0e11"],"state_sha256":"4189a6c83d422e7a09fd112611f2053bb86d3a064da6d2bdf2541207a4b035ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BO8J3IefHyUlhMocxO2xEEfEiDlL5hPc3d7f4qIHvb+GUajTr02eUreqd1doCo4a5Bprgd7FX9aeAz6RXQ2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T21:43:26.240299Z","bundle_sha256":"6c510fcb6f2c1892db40683641edebe29ce30a756619dad103dd91f9ee5f6786"}}