{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZCSVVM4FXEI3BZVZ4MV6QY67ZU","short_pith_number":"pith:ZCSVVM4F","schema_version":"1.0","canonical_sha256":"c8a55ab385b911b0e6b9e32be863dfcd201e6314285b92919d63d2de759c80b7","source":{"kind":"arxiv","id":"2001.11785","version":2},"attestation_state":"computed","paper":{"title":"A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bedour Alrayes, Kostas Stathis, Nicola Paoletti, Pallavi Bagga","submitted_at":"2020-01-31T12:05:46Z","abstract_excerpt":"We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-program"},"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":"2001.11785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-01-31T12:05:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d188a05f458187db4377c14c8e32ab5a555bbee931a668999c7dae718d3a85ee","abstract_canon_sha256":"7c870a4ddafae447d6362793bcf3a774bb6f831a1b2c3118a14fb1b1fbf18dcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:51.557959Z","signature_b64":"9FNtssAajnMu22vgDB+vDn1yqR/Tcx99LSflwxPe7T2P6otXqhzaDzYacdqF0XZuiDu0AAsGGvQG4RhMxW4eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8a55ab385b911b0e6b9e32be863dfcd201e6314285b92919d63d2de759c80b7","last_reissued_at":"2026-07-05T00:37:51.557447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:51.557447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bedour Alrayes, Kostas Stathis, Nicola Paoletti, Pallavi Bagga","submitted_at":"2020-01-31T12:05:46Z","abstract_excerpt":"We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-program"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11785","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.11785/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":"2001.11785","created_at":"2026-07-05T00:37:51.557512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.11785v2","created_at":"2026-07-05T00:37:51.557512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11785","created_at":"2026-07-05T00:37:51.557512+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCSVVM4FXEI3","created_at":"2026-07-05T00:37:51.557512+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCSVVM4FXEI3BZVZ","created_at":"2026-07-05T00:37:51.557512+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCSVVM4F","created_at":"2026-07-05T00:37:51.557512+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/ZCSVVM4FXEI3BZVZ4MV6QY67ZU","json":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU.json","graph_json":"https://pith.science/api/pith-number/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/graph.json","events_json":"https://pith.science/api/pith-number/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/events.json","paper":"https://pith.science/paper/ZCSVVM4F"},"agent_actions":{"view_html":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU","download_json":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU.json","view_paper":"https://pith.science/paper/ZCSVVM4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.11785&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/action/storage_attestation","attest_author":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/action/author_attestation","sign_citation":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/action/citation_signature","submit_replication":"https://pith.science/pith/ZCSVVM4FXEI3BZVZ4MV6QY67ZU/action/replication_record"}},"created_at":"2026-07-05T00:37:51.557512+00:00","updated_at":"2026-07-05T00:37:51.557512+00:00"}