{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MU5IR4PDWJZSNXHXXCDLXFZES7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b65bad43fcbd067807b493abc7649227769370501de12e22e54d90a23467544","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2020-06-10T15:41:58Z","title_canon_sha256":"65a4d43cf276b6e22b81bee8e8a5f8e5e338b9fcc4e584539ae2d8871cb8d16c"},"schema_version":"1.0","source":{"id":"2006.05902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05902","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05902v1","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05902","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"MU5IR4PDWJZS","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"MU5IR4PDWJZSNXHX","created_at":"2026-07-05T01:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"MU5IR4PD","created_at":"2026-07-05T01:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:5a6e6d5098961940bbe946c0e88b3db872168c97d07624599d2a929490a49d6c","target":"graph","created_at":"2026-07-05T01:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.05902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a learning algorithm to find a scheduling policy that achieves an optimal delay-power trade-off in communication systems. Reinforcement learning (RL) is used to minimize the expected latency for a given energy constraint where the environments such as traffic arrival rates or channel conditions can change over time. For this purpose, this problem is formulated as an infinite-horizon Markov Decision Process (MDP) with constraints. To handle the constrained optimization problem, we adopt the Lagrangian relaxation technique to solve it. Then, we propose a variant of Q-learning","authors_text":"Joohyun Lee, Wei Chen, Yu Zhao","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2020-06-10T15:41:58Z","title":"Q-greedyUCB: a New Exploration Policy for Adaptive and Resource-efficient Scheduling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05902","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:244b59b4835b36215223b9d981d93ac1cbb0020127936074a5ba1b9ae98fb954","target":"record","created_at":"2026-07-05T01:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b65bad43fcbd067807b493abc7649227769370501de12e22e54d90a23467544","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2020-06-10T15:41:58Z","title_canon_sha256":"65a4d43cf276b6e22b81bee8e8a5f8e5e338b9fcc4e584539ae2d8871cb8d16c"},"schema_version":"1.0","source":{"id":"2006.05902","kind":"arxiv","version":1}},"canonical_sha256":"653a88f1e3b27326dcf7b886bb972497d51187c42a088a0f7e06b8372baf4426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"653a88f1e3b27326dcf7b886bb972497d51187c42a088a0f7e06b8372baf4426","first_computed_at":"2026-07-05T01:09:18.068251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:18.068251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrOwXd4WQHeUXxbgy52eqDnu/n8nBpmBWRvzuDtCWBmKZ7GV1LUvOuKcOzu3l6spcBekLWIC2mRezE5U2P0vBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:18.068670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:244b59b4835b36215223b9d981d93ac1cbb0020127936074a5ba1b9ae98fb954","sha256:5a6e6d5098961940bbe946c0e88b3db872168c97d07624599d2a929490a49d6c"],"state_sha256":"345f3322d6ca42a8db8ab959fea82b084dbbd723cfd88767c3d6e0a82504108a"}