{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6DTDNU2OFBHPUPIMFEBNNVXJ3A","short_pith_number":"pith:6DTDNU2O","schema_version":"1.0","canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","source":{"kind":"arxiv","id":"1905.13428","version":1},"attestation_state":"computed","paper":{"title":"Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew A. Wright, Roberto Horowitz","submitted_at":"2019-05-31T06:02:52Z","abstract_excerpt":"Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share"},"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":"1905.13428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T06:02:52Z","cross_cats_sorted":["cs.MA","cs.SY","stat.ML"],"title_canon_sha256":"3b9ca0edfe7e6739ba1938c00456be91ea15c3567f8e02089eb4dded8c376cc5","abstract_canon_sha256":"61285761945103766d6a3e07ba643659bbddbdefed879b761a76d0dcf98bee7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.931449Z","signature_b64":"ZLxPi+bfXrJ86aJuxiyYxJePkKzdtlqWtxNeslvm8fvf2QtSu+an9PaEx8wvzTDniMD/5/TVbh3rztr6AKS+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0e636d34e284efa3d0c2902d6d6e9d83e8b8b064845c771dcfa95134ae8965d","last_reissued_at":"2026-05-17T23:44:34.930961Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.930961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew A. Wright, Roberto Horowitz","submitted_at":"2019-05-31T06:02:52Z","abstract_excerpt":"Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13428","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":"1905.13428","created_at":"2026-05-17T23:44:34.931034+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13428v1","created_at":"2026-05-17T23:44:34.931034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13428","created_at":"2026-05-17T23:44:34.931034+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DTDNU2OFBHP","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DTDNU2OFBHPUPIM","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DTDNU2O","created_at":"2026-05-18T12:33:10.108867+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/6DTDNU2OFBHPUPIMFEBNNVXJ3A","json":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A.json","graph_json":"https://pith.science/api/pith-number/6DTDNU2OFBHPUPIMFEBNNVXJ3A/graph.json","events_json":"https://pith.science/api/pith-number/6DTDNU2OFBHPUPIMFEBNNVXJ3A/events.json","paper":"https://pith.science/paper/6DTDNU2O"},"agent_actions":{"view_html":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A","download_json":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A.json","view_paper":"https://pith.science/paper/6DTDNU2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13428&json=true","fetch_graph":"https://pith.science/api/pith-number/6DTDNU2OFBHPUPIMFEBNNVXJ3A/graph.json","fetch_events":"https://pith.science/api/pith-number/6DTDNU2OFBHPUPIMFEBNNVXJ3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/action/storage_attestation","attest_author":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/action/author_attestation","sign_citation":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/action/citation_signature","submit_replication":"https://pith.science/pith/6DTDNU2OFBHPUPIMFEBNNVXJ3A/action/replication_record"}},"created_at":"2026-05-17T23:44:34.931034+00:00","updated_at":"2026-05-17T23:44:34.931034+00:00"}