{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PMPQ6P7B2SZEWY7ILIA5HXSSIV","short_pith_number":"pith:PMPQ6P7B","schema_version":"1.0","canonical_sha256":"7b1f0f3fe1d4b24b63e85a01d3de524572c8a507588f709647de74b4e8fe17d7","source":{"kind":"arxiv","id":"1708.05565","version":2},"attestation_state":"computed","paper":{"title":"LADDER: A Human-Level Bidding Agent for Large-Scale Real-Time Online Auctions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GT"],"primary_cat":"cs.LG","authors_text":"Jiayi Liu, Jinghe Hu, Jun Hao, Mantian Li, Weipeng P. Yan, Yang He, Yu Wang, Yuxiang Liu","submitted_at":"2017-08-18T11:25:30Z","abstract_excerpt":"We present LADDER, the first deep reinforcement learning agent that can successfully learn control policies for large-scale real-world problems directly from raw inputs composed of high-level semantic information. The agent is based on an asynchronous stochastic variant of DQN (Deep Q Network) named DASQN. The inputs of the agent are plain-text descriptions of states of a game of incomplete information, i.e. real-time large scale online auctions, and the rewards are auction profits of very large scale. We apply the agent to an essential portion of JD's online RTB (real-time bidding) advertisin"},"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":"1708.05565","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-18T11:25:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.GT"],"title_canon_sha256":"e9df922f45f536e396d19998ea6b1fef108b3b7d5a1b694268ae76bab1dbc609","abstract_canon_sha256":"d201f3682d4189369d2ab6adb4ed5d794d68ce71730ec3542c23ce00c6fb67fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:13.749744Z","signature_b64":"hk0QDc3WPgLFgn6Yk5IhFfcmKDe3tJXMt/Kf5ZzQb+9UX+nKeWg4i0PXJxxXGZHwMbwThcpaq+D4nxtStfgVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b1f0f3fe1d4b24b63e85a01d3de524572c8a507588f709647de74b4e8fe17d7","last_reissued_at":"2026-05-18T00:36:13.749081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:13.749081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LADDER: A Human-Level Bidding Agent for Large-Scale Real-Time Online Auctions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GT"],"primary_cat":"cs.LG","authors_text":"Jiayi Liu, Jinghe Hu, Jun Hao, Mantian Li, Weipeng P. Yan, Yang He, Yu Wang, Yuxiang Liu","submitted_at":"2017-08-18T11:25:30Z","abstract_excerpt":"We present LADDER, the first deep reinforcement learning agent that can successfully learn control policies for large-scale real-world problems directly from raw inputs composed of high-level semantic information. The agent is based on an asynchronous stochastic variant of DQN (Deep Q Network) named DASQN. The inputs of the agent are plain-text descriptions of states of a game of incomplete information, i.e. real-time large scale online auctions, and the rewards are auction profits of very large scale. We apply the agent to an essential portion of JD's online RTB (real-time bidding) advertisin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05565","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":""},"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":"1708.05565","created_at":"2026-05-18T00:36:13.749186+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05565v2","created_at":"2026-05-18T00:36:13.749186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05565","created_at":"2026-05-18T00:36:13.749186+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMPQ6P7B2SZE","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMPQ6P7B2SZEWY7I","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMPQ6P7B","created_at":"2026-05-18T12:31:37.085036+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/PMPQ6P7B2SZEWY7ILIA5HXSSIV","json":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV.json","graph_json":"https://pith.science/api/pith-number/PMPQ6P7B2SZEWY7ILIA5HXSSIV/graph.json","events_json":"https://pith.science/api/pith-number/PMPQ6P7B2SZEWY7ILIA5HXSSIV/events.json","paper":"https://pith.science/paper/PMPQ6P7B"},"agent_actions":{"view_html":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV","download_json":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV.json","view_paper":"https://pith.science/paper/PMPQ6P7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05565&json=true","fetch_graph":"https://pith.science/api/pith-number/PMPQ6P7B2SZEWY7ILIA5HXSSIV/graph.json","fetch_events":"https://pith.science/api/pith-number/PMPQ6P7B2SZEWY7ILIA5HXSSIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV/action/storage_attestation","attest_author":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV/action/author_attestation","sign_citation":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV/action/citation_signature","submit_replication":"https://pith.science/pith/PMPQ6P7B2SZEWY7ILIA5HXSSIV/action/replication_record"}},"created_at":"2026-05-18T00:36:13.749186+00:00","updated_at":"2026-05-18T00:36:13.749186+00:00"}