{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OJLHTSKEUTAMJ2GYW7ACEN7YIH","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":"104897ad23b7d2f169f32e872a873bb07d6a6c5d2e59a07f1ed3e6012b1ce46a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T07:35:02Z","title_canon_sha256":"8bcaaa5d6e55f620caffc70a11e714154a49f8a427cf1e4ee60cc570a761fb00"},"schema_version":"1.0","source":{"id":"1906.02457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02457","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02457v1","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02457","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"pith_short_12","alias_value":"OJLHTSKEUTAM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OJLHTSKEUTAMJ2GY","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OJLHTSKE","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:de0287a6a0054203f5ed69b6192196117c04f60a6115e959e42d39ed2aeb41d0","target":"graph","created_at":"2026-05-17T23:44:01Z","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":"Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards. During exploration, the agent tries to discover novel areas or high reward~(quality) areas. In most existing methods, the novelty and quality in the neighboring area of the current state are not well utilized to guide the exploration of the agent. To tackle this problem, we propose a novel RL framework, called \\underline{c}lustered \\underline{r}einforcement \\underline{l}earning~(CRL), for efficient exploration in RL. CRL ","authors_text":"Shen-Yi Zhao, Wu-Jun Li, Xiao Ma","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T07:35:02Z","title":"Clustered Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02457","kind":"arxiv","version":1},"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":"sha256:2968f48a5990a3266000a4d41fbf69526feae6b0ee52a8ce165cb1d0204dea6f","target":"record","created_at":"2026-05-17T23:44:01Z","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":"104897ad23b7d2f169f32e872a873bb07d6a6c5d2e59a07f1ed3e6012b1ce46a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T07:35:02Z","title_canon_sha256":"8bcaaa5d6e55f620caffc70a11e714154a49f8a427cf1e4ee60cc570a761fb00"},"schema_version":"1.0","source":{"id":"1906.02457","kind":"arxiv","version":1}},"canonical_sha256":"725679c944a4c0c4e8d8b7c02237f841c865e6f182a86db02c1e7b1e00bf3cd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"725679c944a4c0c4e8d8b7c02237f841c865e6f182a86db02c1e7b1e00bf3cd7","first_computed_at":"2026-05-17T23:44:01.115136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:01.115136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E+ETPpN99+0nKHR2xaDBTcz4P6YB2dzTorVA4b9fzLWogpLqp9gLC4TVz03UgI3/QXFivyfrgJmIl1CxqaiwCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:01.115763Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2968f48a5990a3266000a4d41fbf69526feae6b0ee52a8ce165cb1d0204dea6f","sha256:de0287a6a0054203f5ed69b6192196117c04f60a6115e959e42d39ed2aeb41d0"],"state_sha256":"8674394f7a0be2a66028247c4ec2e4587a206705049b9a8ffae17a1e9a61c406"}