{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CEWQGVVPKVXUR4GOAR7ABLSPL3","short_pith_number":"pith:CEWQGVVP","schema_version":"1.0","canonical_sha256":"112d0356af556f48f0ce047e00ae4f5ecd80c1b1d6070f712936ee5c83b72c34","source":{"kind":"arxiv","id":"2506.07046","version":1},"attestation_state":"computed","paper":{"title":"QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO","eess.IV"],"primary_cat":"cs.AR","authors_text":"Anushka Jha, Mukul Lokhande, Santosh Kumar Vishvakarma, Tanushree Dewangan","submitted_at":"2025-06-08T08:55:49Z","abstract_excerpt":"Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degradation. QForce-RL takes advantages from E2HRL to reduce overall RL actions to learn desired policy and "},"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":"2506.07046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-06-08T08:55:49Z","cross_cats_sorted":["cs.CV","cs.RO","eess.IV"],"title_canon_sha256":"f1de25ccd2595222667b79cf8d682971c7f726763e18f0a83fcb09b063bc135f","abstract_canon_sha256":"67ad17b078c89ded020c21c2d1490f6ea1470160ef78166c693142170843b593"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:00.183374Z","signature_b64":"wj8T2A3ActrM/RggLf9uYHuao+Ka3ZUSbJOF+nUAiTeZTbbkUqKRYuPaiPz1SjN3smTO8mMS3K5tanq72mp2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"112d0356af556f48f0ce047e00ae4f5ecd80c1b1d6070f712936ee5c83b72c34","last_reissued_at":"2026-07-05T11:18:00.182880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:00.182880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QForce-RL: Quantized FPGA-Optimized Reinforcement Learning Compute Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO","eess.IV"],"primary_cat":"cs.AR","authors_text":"Anushka Jha, Mukul Lokhande, Santosh Kumar Vishvakarma, Tanushree Dewangan","submitted_at":"2025-06-08T08:55:49Z","abstract_excerpt":"Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degradation. QForce-RL takes advantages from E2HRL to reduce overall RL actions to learn desired policy and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07046","kind":"arxiv","version":1},"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/2506.07046/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":"2506.07046","created_at":"2026-07-05T11:18:00.182939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07046v1","created_at":"2026-07-05T11:18:00.182939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07046","created_at":"2026-07-05T11:18:00.182939+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEWQGVVPKVXU","created_at":"2026-07-05T11:18:00.182939+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEWQGVVPKVXUR4GO","created_at":"2026-07-05T11:18:00.182939+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEWQGVVP","created_at":"2026-07-05T11:18:00.182939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24273","citing_title":"BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3","json":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3.json","graph_json":"https://pith.science/api/pith-number/CEWQGVVPKVXUR4GOAR7ABLSPL3/graph.json","events_json":"https://pith.science/api/pith-number/CEWQGVVPKVXUR4GOAR7ABLSPL3/events.json","paper":"https://pith.science/paper/CEWQGVVP"},"agent_actions":{"view_html":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3","download_json":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3.json","view_paper":"https://pith.science/paper/CEWQGVVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07046&json=true","fetch_graph":"https://pith.science/api/pith-number/CEWQGVVPKVXUR4GOAR7ABLSPL3/graph.json","fetch_events":"https://pith.science/api/pith-number/CEWQGVVPKVXUR4GOAR7ABLSPL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3/action/storage_attestation","attest_author":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3/action/author_attestation","sign_citation":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3/action/citation_signature","submit_replication":"https://pith.science/pith/CEWQGVVPKVXUR4GOAR7ABLSPL3/action/replication_record"}},"created_at":"2026-07-05T11:18:00.182939+00:00","updated_at":"2026-07-05T11:18:00.182939+00:00"}