{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RE62ZCVLJ6OJ5RPUDSAQGAWAE5","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":"ef5835dc810ce2e4f9933a5a2dde255ae09ef640801b64bdcbc0a1db3089e11d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-02T13:05:24Z","title_canon_sha256":"5a81fa940c389795043d4772632bafc809466af4027885e3f33497a7fe12f678"},"schema_version":"1.0","source":{"id":"2106.01134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01134","created_at":"2026-07-05T02:45:44Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01134v1","created_at":"2026-07-05T02:45:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01134","created_at":"2026-07-05T02:45:44Z"},{"alias_kind":"pith_short_12","alias_value":"RE62ZCVLJ6OJ","created_at":"2026-07-05T02:45:44Z"},{"alias_kind":"pith_short_16","alias_value":"RE62ZCVLJ6OJ5RPU","created_at":"2026-07-05T02:45:44Z"},{"alias_kind":"pith_short_8","alias_value":"RE62ZCVL","created_at":"2026-07-05T02:45:44Z"}],"graph_snapshots":[{"event_id":"sha256:a5c0e9954123c25a86e98284ac850773efe61946b7d85cc19c53a7696b3a2503","target":"graph","created_at":"2026-07-05T02:45:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.01134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An improvement of Q-learning is proposed in this paper. It is different from classic Q-learning in that the similarity between different states and actions is considered in the proposed method. During the training, a new updating mechanism is used, in which the Q value of the similar state-action pairs are updated synchronously. The proposed method can be used in combination with both tabular Q-learning function and deep Q-learning. And the results of numerical examples illustrate that compared to the classic Q-learning, the proposed method has a significantly better performance.","authors_text":"Jizhou Lai, Wei Liao, Xiaohui Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-02T13:05:24Z","title":"Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01134","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:a8897cb67061bda2058313ff65328fa12a2da7e92699ea65067cddd09e4385fc","target":"record","created_at":"2026-07-05T02:45:44Z","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":"ef5835dc810ce2e4f9933a5a2dde255ae09ef640801b64bdcbc0a1db3089e11d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-02T13:05:24Z","title_canon_sha256":"5a81fa940c389795043d4772632bafc809466af4027885e3f33497a7fe12f678"},"schema_version":"1.0","source":{"id":"2106.01134","kind":"arxiv","version":1}},"canonical_sha256":"893dac8aab4f9c9ec5f41c810302c02776ae88978494d3b176727f9418471cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"893dac8aab4f9c9ec5f41c810302c02776ae88978494d3b176727f9418471cd2","first_computed_at":"2026-07-05T02:45:44.162928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:44.162928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qOBc/TryqEAd0pbo0HTQMOG9zbus+qWA8AGeFmujGrefSGzyUI6IrB0ahfHB5iQ0Id+Fy2bTLimDh1F1RtKPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:44.163372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8897cb67061bda2058313ff65328fa12a2da7e92699ea65067cddd09e4385fc","sha256:a5c0e9954123c25a86e98284ac850773efe61946b7d85cc19c53a7696b3a2503"],"state_sha256":"31afc2431617b30728c7b067d77dbce324cdcd39a1d570835b9614d950596d0a"}