{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5XPQQZCHI4GPULV6IDFOMMP3AM","short_pith_number":"pith:5XPQQZCH","schema_version":"1.0","canonical_sha256":"eddf086447470cfa2ebe40cae631fb03128503c55329cddf327dc86716bbbb71","source":{"kind":"arxiv","id":"2305.07448","version":2},"attestation_state":"computed","paper":{"title":"Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Bolun Zhang, Nguyen Van Huynh","submitted_at":"2023-05-12T13:05:32Z","abstract_excerpt":"End-to-End (E2E) learning-based concept has been recently introduced to jointly optimize both the transmitter and the receiver in wireless communication systems. Unfortunately, this E2E learning architecture requires a prior differentiable channel model to jointly train the deep neural networks (DNNs) at the transceivers, which is hardly obtained in practice. This paper aims to solve this issue by developing a deep deterministic policy gradient (DDPG)-based framework. In particular, the proposed solution uses the loss value of the receiver DNN as the reward to train the transmitter DNN. The si"},"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":"2305.07448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2023-05-12T13:05:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5d1e589e7d314647c6af5d0acf3766a353d1600a5240df6487c261e3a5e69076","abstract_canon_sha256":"f52cf37f923eb9dd0dbda8a59c30bf5e1e2548dbf8d63500d94281e0ad354d2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:59.432109Z","signature_b64":"XdKpN52sE8Q+7UqFHE1kUiwtPB/eqHoRFladDQXu0gVs1u3w2FGJTco9YGgT+1Cx9PErtJzgU1ZzOpHDLKc0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eddf086447470cfa2ebe40cae631fb03128503c55329cddf327dc86716bbbb71","last_reissued_at":"2026-07-05T06:37:59.431621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:59.431621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Bolun Zhang, Nguyen Van Huynh","submitted_at":"2023-05-12T13:05:32Z","abstract_excerpt":"End-to-End (E2E) learning-based concept has been recently introduced to jointly optimize both the transmitter and the receiver in wireless communication systems. Unfortunately, this E2E learning architecture requires a prior differentiable channel model to jointly train the deep neural networks (DNNs) at the transceivers, which is hardly obtained in practice. This paper aims to solve this issue by developing a deep deterministic policy gradient (DDPG)-based framework. In particular, the proposed solution uses the loss value of the receiver DNN as the reward to train the transmitter DNN. The si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07448","kind":"arxiv","version":2},"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/2305.07448/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":"2305.07448","created_at":"2026-07-05T06:37:59.431692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07448v2","created_at":"2026-07-05T06:37:59.431692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07448","created_at":"2026-07-05T06:37:59.431692+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XPQQZCHI4GP","created_at":"2026-07-05T06:37:59.431692+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XPQQZCHI4GPULV6","created_at":"2026-07-05T06:37:59.431692+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XPQQZCH","created_at":"2026-07-05T06:37:59.431692+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/5XPQQZCHI4GPULV6IDFOMMP3AM","json":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM.json","graph_json":"https://pith.science/api/pith-number/5XPQQZCHI4GPULV6IDFOMMP3AM/graph.json","events_json":"https://pith.science/api/pith-number/5XPQQZCHI4GPULV6IDFOMMP3AM/events.json","paper":"https://pith.science/paper/5XPQQZCH"},"agent_actions":{"view_html":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM","download_json":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM.json","view_paper":"https://pith.science/paper/5XPQQZCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07448&json=true","fetch_graph":"https://pith.science/api/pith-number/5XPQQZCHI4GPULV6IDFOMMP3AM/graph.json","fetch_events":"https://pith.science/api/pith-number/5XPQQZCHI4GPULV6IDFOMMP3AM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM/action/storage_attestation","attest_author":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM/action/author_attestation","sign_citation":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM/action/citation_signature","submit_replication":"https://pith.science/pith/5XPQQZCHI4GPULV6IDFOMMP3AM/action/replication_record"}},"created_at":"2026-07-05T06:37:59.431692+00:00","updated_at":"2026-07-05T06:37:59.431692+00:00"}