{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JUOMH4S3ONWUGGEEGV6KPDYBHA","short_pith_number":"pith:JUOMH4S3","schema_version":"1.0","canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","source":{"kind":"arxiv","id":"2311.11423","version":1},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","eess.SP","math.IT"],"primary_cat":"cs.IT","authors_text":"Cong Shen, Jerry Sydir, Jing Yang, Kun Yang, Shu-ping Yeh","submitted_at":"2023-11-19T21:02:17Z","abstract_excerpt":"The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first investigate the use of \\emph{offline} RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms, including behavior constrained Q-learning (BCQ), conservative Q-learning (CQL), and implicit Q-learning (IQL), for "},"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":"2311.11423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2023-11-19T21:02:17Z","cross_cats_sorted":["cs.LG","cs.NI","eess.SP","math.IT"],"title_canon_sha256":"040186652992efed01e799a1a12bc85191fde6c0ed754e1076f43e085675f73d","abstract_canon_sha256":"d4468292dd3765a632c74a830fa31f574e96b2197ecf90fd36ea32cff872ce90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:32.853436Z","signature_b64":"3w56PTPkw7x1ftq+FPjzJN8i/fa7349WQF2SRKrJ9hukHvfa1JdggPkZYNQjjY0Do3gqBWbBfYMFQBJuC97qDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1cc3f25b736d431884357ca78f01380d04ed5e2e1d28fc3f197f6103599406","last_reissued_at":"2026-07-05T07:14:32.852959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:32.852959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","eess.SP","math.IT"],"primary_cat":"cs.IT","authors_text":"Cong Shen, Jerry Sydir, Jing Yang, Kun Yang, Shu-ping Yeh","submitted_at":"2023-11-19T21:02:17Z","abstract_excerpt":"The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first investigate the use of \\emph{offline} RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms, including behavior constrained Q-learning (BCQ), conservative Q-learning (CQL), and implicit Q-learning (IQL), for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11423","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/2311.11423/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":"2311.11423","created_at":"2026-07-05T07:14:32.853017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11423v1","created_at":"2026-07-05T07:14:32.853017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11423","created_at":"2026-07-05T07:14:32.853017+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUOMH4S3ONWU","created_at":"2026-07-05T07:14:32.853017+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUOMH4S3ONWUGGEE","created_at":"2026-07-05T07:14:32.853017+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUOMH4S3","created_at":"2026-07-05T07:14:32.853017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13768","citing_title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA","json":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA.json","graph_json":"https://pith.science/api/pith-number/JUOMH4S3ONWUGGEEGV6KPDYBHA/graph.json","events_json":"https://pith.science/api/pith-number/JUOMH4S3ONWUGGEEGV6KPDYBHA/events.json","paper":"https://pith.science/paper/JUOMH4S3"},"agent_actions":{"view_html":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA","download_json":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA.json","view_paper":"https://pith.science/paper/JUOMH4S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11423&json=true","fetch_graph":"https://pith.science/api/pith-number/JUOMH4S3ONWUGGEEGV6KPDYBHA/graph.json","fetch_events":"https://pith.science/api/pith-number/JUOMH4S3ONWUGGEEGV6KPDYBHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/action/storage_attestation","attest_author":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/action/author_attestation","sign_citation":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/action/citation_signature","submit_replication":"https://pith.science/pith/JUOMH4S3ONWUGGEEGV6KPDYBHA/action/replication_record"}},"created_at":"2026-07-05T07:14:32.853017+00:00","updated_at":"2026-07-05T07:14:32.853017+00:00"}