{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2MC523IYB337ASCOF77IFJ2AAG","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":"3d71086027c613b64e0313d44fddc35553bac8ca9a28fa03ddded17cbe0b886e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-19T14:33:00Z","title_canon_sha256":"3debecef1753e32cc082c045ecd25547df775e87daaf08d13b18299a44ae2dc0"},"schema_version":"1.0","source":{"id":"1805.07603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07603","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07603v1","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07603","created_at":"2026-05-18T00:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"2MC523IYB337","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2MC523IYB337ASCO","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2MC523IY","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:4ff3a6676a354bf66ed203487ef0ae3b9c1f82f15a1d7c540bb0578870083309","target":"graph","created_at":"2026-05-18T00:15:33Z","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":"Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently, episodic memory based RL has attracted attention due to its ability to latch on good actions quickly. In this paper, we present a simple yet effective biologically inspired RL algorithm called Episodic Memory Deep Q-Networks (EMDQN), which leverages episodic memory to supervise ","authors_text":"Guangwen Yang, Lintao Zhang, Tianqi Zhao, Zichuan Lin","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-19T14:33:00Z","title":"Episodic Memory Deep Q-Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07603","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":"sha256:977cb7988ff9e45546824922b40c72911508d905df974459451b4a8b7f20afca","target":"record","created_at":"2026-05-18T00:15:33Z","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":"3d71086027c613b64e0313d44fddc35553bac8ca9a28fa03ddded17cbe0b886e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-19T14:33:00Z","title_canon_sha256":"3debecef1753e32cc082c045ecd25547df775e87daaf08d13b18299a44ae2dc0"},"schema_version":"1.0","source":{"id":"1805.07603","kind":"arxiv","version":1}},"canonical_sha256":"d305dd6d180ef7f0484e2ffe82a740018edf9a3dab7790ab6f3b273cfae91ab8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d305dd6d180ef7f0484e2ffe82a740018edf9a3dab7790ab6f3b273cfae91ab8","first_computed_at":"2026-05-18T00:15:33.092016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:33.092016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6NJpwCuzc2OXgcPCEIj+46lgYn2LQ2QtwNG/gYqxZpNyaEyYnaSIOTCfbusQsDaBGngjQnIMATCq7/F8SrZDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:33.092639Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:977cb7988ff9e45546824922b40c72911508d905df974459451b4a8b7f20afca","sha256:4ff3a6676a354bf66ed203487ef0ae3b9c1f82f15a1d7c540bb0578870083309"],"state_sha256":"f89d9fe7a986d97607c4bcf53cd1c8caf63106b93384922b3fcdac6b0b916c39"}