{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHGGQSPLUWGJ6UEY3MG76NLXV2","short_pith_number":"pith:GHGGQSPL","schema_version":"1.0","canonical_sha256":"31cc6849eba58c9f5098db0dff3577ae9b5b060db384fcb3d7913a1596fc7c59","source":{"kind":"arxiv","id":"2303.16685","version":1},"attestation_state":"computed","paper":{"title":"Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NI","authors_text":"Di Wu, Gregory Dudek, Jimmy Li, Michael Jenkin, Seowoo Jang, Xue Liu, Yi Tian Xu","submitted_at":"2023-03-22T22:27:00Z","abstract_excerpt":"With the continuous growth in communication network complexity and traffic volume, communication load balancing solutions are receiving increasing attention. Specifically, reinforcement learning (RL)-based methods have shown impressive performance compared with traditional rule-based methods. However, standard RL methods generally require an enormous amount of data to train, and generalize poorly to scenarios that are not encountered during training. We propose a policy reuse framework in which a policy selector chooses the most suitable pre-trained RL policy to execute based on the current tr"},"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":"2303.16685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2023-03-22T22:27:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e17efade78b3ebcd8e268b4e4e3158c10148fdd5d0ddaa713789afe68cb2d2a","abstract_canon_sha256":"c69b66398c165bbf52ce6125bdd7576bb746211f8df9fc86704535b021aecd49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:09.238363Z","signature_b64":"hc5MM05yftMYz6UzlFdoHgqbOTTe0HnVkjfqH9VthaFNjuppHTlQubOFuDdKXpmZdjUTC5jVzw/tZaP4fxB5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31cc6849eba58c9f5098db0dff3577ae9b5b060db384fcb3d7913a1596fc7c59","last_reissued_at":"2026-07-05T05:56:09.237949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:09.237949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NI","authors_text":"Di Wu, Gregory Dudek, Jimmy Li, Michael Jenkin, Seowoo Jang, Xue Liu, Yi Tian Xu","submitted_at":"2023-03-22T22:27:00Z","abstract_excerpt":"With the continuous growth in communication network complexity and traffic volume, communication load balancing solutions are receiving increasing attention. Specifically, reinforcement learning (RL)-based methods have shown impressive performance compared with traditional rule-based methods. However, standard RL methods generally require an enormous amount of data to train, and generalize poorly to scenarios that are not encountered during training. We propose a policy reuse framework in which a policy selector chooses the most suitable pre-trained RL policy to execute based on the current tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16685","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/2303.16685/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":"2303.16685","created_at":"2026-07-05T05:56:09.238007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16685v1","created_at":"2026-07-05T05:56:09.238007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16685","created_at":"2026-07-05T05:56:09.238007+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHGGQSPLUWGJ","created_at":"2026-07-05T05:56:09.238007+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHGGQSPLUWGJ6UEY","created_at":"2026-07-05T05:56:09.238007+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHGGQSPL","created_at":"2026-07-05T05:56:09.238007+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/GHGGQSPLUWGJ6UEY3MG76NLXV2","json":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2.json","graph_json":"https://pith.science/api/pith-number/GHGGQSPLUWGJ6UEY3MG76NLXV2/graph.json","events_json":"https://pith.science/api/pith-number/GHGGQSPLUWGJ6UEY3MG76NLXV2/events.json","paper":"https://pith.science/paper/GHGGQSPL"},"agent_actions":{"view_html":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2","download_json":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2.json","view_paper":"https://pith.science/paper/GHGGQSPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16685&json=true","fetch_graph":"https://pith.science/api/pith-number/GHGGQSPLUWGJ6UEY3MG76NLXV2/graph.json","fetch_events":"https://pith.science/api/pith-number/GHGGQSPLUWGJ6UEY3MG76NLXV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2/action/storage_attestation","attest_author":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2/action/author_attestation","sign_citation":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2/action/citation_signature","submit_replication":"https://pith.science/pith/GHGGQSPLUWGJ6UEY3MG76NLXV2/action/replication_record"}},"created_at":"2026-07-05T05:56:09.238007+00:00","updated_at":"2026-07-05T05:56:09.238007+00:00"}