{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VUQOLBPTQ3ZA5T7Y767HWI3BC4","short_pith_number":"pith:VUQOLBPT","schema_version":"1.0","canonical_sha256":"ad20e585f386f20ecff8ffbe7b2361171152d4b551c0f3763986c4598c267868","source":{"kind":"arxiv","id":"2201.07211","version":3},"attestation_state":"computed","paper":{"title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Guisong Liu, Huajin Tang, Li Huang, Wenjie Deng, Xiurui Xie","submitted_at":"2021-12-13T09:46:17Z","abstract_excerpt":"As the third-generation neural networks, Spiking Neural Networks (SNNs) have great potential on neuromorphic hardware because of their high energy-efficiency. However, Deep Spiking Reinforcement Learning (DSRL), i.e., the Reinforcement Learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the non-differentiable property of the spiking function. To address these issues, we propose a Deep Spiking Q-Network (DSQN) in this paper. Specifically, we propose a directly-trained deep spiking reinforcement learning architecture based on the Leaky Integrate-and-Fire ("},"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":"2201.07211","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2021-12-13T09:46:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"03e85978a4cd08925f4c2a1b116173ed6dc2838adb8da15a0ce17537e94bb5c7","abstract_canon_sha256":"bb27200f5bb95be1c1a9c9fb93df6078a1e50f0da58f4ac3f1f7392ddf93b314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:32.350798Z","signature_b64":"9V0G5jOkHcOyN4KUoiK0EMJDLh7tnLZ+AYikeX1jBOjwIOxFPDSUGhsHFQeL9mxhjGKEuHhTmC9/xtdDWS2oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad20e585f386f20ecff8ffbe7b2361171152d4b551c0f3763986c4598c267868","last_reissued_at":"2026-07-05T05:59:32.350381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:32.350381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Guisong Liu, Huajin Tang, Li Huang, Wenjie Deng, Xiurui Xie","submitted_at":"2021-12-13T09:46:17Z","abstract_excerpt":"As the third-generation neural networks, Spiking Neural Networks (SNNs) have great potential on neuromorphic hardware because of their high energy-efficiency. However, Deep Spiking Reinforcement Learning (DSRL), i.e., the Reinforcement Learning (RL) based on SNNs, is still in its preliminary stage due to the binary output and the non-differentiable property of the spiking function. To address these issues, we propose a Deep Spiking Q-Network (DSQN) in this paper. Specifically, we propose a directly-trained deep spiking reinforcement learning architecture based on the Leaky Integrate-and-Fire ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07211","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.07211/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2201.07211","created_at":"2026-07-05T05:59:32.350438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07211v3","created_at":"2026-07-05T05:59:32.350438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07211","created_at":"2026-07-05T05:59:32.350438+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUQOLBPTQ3ZA","created_at":"2026-07-05T05:59:32.350438+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUQOLBPTQ3ZA5T7Y","created_at":"2026-07-05T05:59:32.350438+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUQOLBPT","created_at":"2026-07-05T05:59:32.350438+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/VUQOLBPTQ3ZA5T7Y767HWI3BC4","json":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4.json","graph_json":"https://pith.science/api/pith-number/VUQOLBPTQ3ZA5T7Y767HWI3BC4/graph.json","events_json":"https://pith.science/api/pith-number/VUQOLBPTQ3ZA5T7Y767HWI3BC4/events.json","paper":"https://pith.science/paper/VUQOLBPT"},"agent_actions":{"view_html":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4","download_json":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4.json","view_paper":"https://pith.science/paper/VUQOLBPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07211&json=true","fetch_graph":"https://pith.science/api/pith-number/VUQOLBPTQ3ZA5T7Y767HWI3BC4/graph.json","fetch_events":"https://pith.science/api/pith-number/VUQOLBPTQ3ZA5T7Y767HWI3BC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4/action/storage_attestation","attest_author":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4/action/author_attestation","sign_citation":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4/action/citation_signature","submit_replication":"https://pith.science/pith/VUQOLBPTQ3ZA5T7Y767HWI3BC4/action/replication_record"}},"created_at":"2026-07-05T05:59:32.350438+00:00","updated_at":"2026-07-05T05:59:32.350438+00:00"}