{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L6MKXRRN2GNDMVMBLB7EVPCGPL","short_pith_number":"pith:L6MKXRRN","schema_version":"1.0","canonical_sha256":"5f98abc62dd19a365581587e4abc467ad075d894ef885027893af6de194cbbc3","source":{"kind":"arxiv","id":"1810.07862","version":1},"attestation_state":"computed","paper":{"title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Dinh Thai Hoang, Dong In Kim, Dusit Niyato, Nguyen Cong Luong, Ping Wang, Shimin Gong, Ying-Chang Liang","submitted_at":"2018-10-18T01:47:19Z","abstract_excerpt":"This paper presents a comprehensive literature review on applications of deep reinforcement learning in communications and networking. Modern networks, e.g., Internet of Things (IoT) and Unmanned Aerial Vehicle (UAV) networks, become more decentralized and autonomous. In such networks, network entities need to make decisions locally to maximize the network performance under uncertainty of network environment. Reinforcement learning has been efficiently used to enable the network entities to obtain the optimal policy including, e.g., decisions or actions, given their states when the state and a"},"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":"1810.07862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2018-10-18T01:47:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a64396224ab597b65435a21a3ecda437e2b9bd399556e8f14fe08e609b5ec8b","abstract_canon_sha256":"62def7c15c0883cf86f0baa1d3c3ca8eb53ced9e35e613c78f0b1da03b24d94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:54.005197Z","signature_b64":"JGE72BzYvmkFdkoxj1V4/KMj0x4X+gOL6GzTdYg2/rf5T0vNETwMc9U+2f7fj+wYr/CkcOHIPYa4dVNX9cgTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f98abc62dd19a365581587e4abc467ad075d894ef885027893af6de194cbbc3","last_reissued_at":"2026-05-18T00:02:54.004612Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:54.004612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NI","authors_text":"Dinh Thai Hoang, Dong In Kim, Dusit Niyato, Nguyen Cong Luong, Ping Wang, Shimin Gong, Ying-Chang Liang","submitted_at":"2018-10-18T01:47:19Z","abstract_excerpt":"This paper presents a comprehensive literature review on applications of deep reinforcement learning in communications and networking. Modern networks, e.g., Internet of Things (IoT) and Unmanned Aerial Vehicle (UAV) networks, become more decentralized and autonomous. In such networks, network entities need to make decisions locally to maximize the network performance under uncertainty of network environment. Reinforcement learning has been efficiently used to enable the network entities to obtain the optimal policy including, e.g., decisions or actions, given their states when the state and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07862","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":""},"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":"1810.07862","created_at":"2026-05-18T00:02:54.004698+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07862v1","created_at":"2026-05-18T00:02:54.004698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07862","created_at":"2026-05-18T00:02:54.004698+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6MKXRRN2GND","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6MKXRRN2GNDMVMB","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6MKXRRN","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08965","citing_title":"Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges","ref_index":111,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL","json":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL.json","graph_json":"https://pith.science/api/pith-number/L6MKXRRN2GNDMVMBLB7EVPCGPL/graph.json","events_json":"https://pith.science/api/pith-number/L6MKXRRN2GNDMVMBLB7EVPCGPL/events.json","paper":"https://pith.science/paper/L6MKXRRN"},"agent_actions":{"view_html":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL","download_json":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL.json","view_paper":"https://pith.science/paper/L6MKXRRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07862&json=true","fetch_graph":"https://pith.science/api/pith-number/L6MKXRRN2GNDMVMBLB7EVPCGPL/graph.json","fetch_events":"https://pith.science/api/pith-number/L6MKXRRN2GNDMVMBLB7EVPCGPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL/action/storage_attestation","attest_author":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL/action/author_attestation","sign_citation":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL/action/citation_signature","submit_replication":"https://pith.science/pith/L6MKXRRN2GNDMVMBLB7EVPCGPL/action/replication_record"}},"created_at":"2026-05-18T00:02:54.004698+00:00","updated_at":"2026-05-18T00:02:54.004698+00:00"}