{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LTT5MXV6HTC3KQCOSA7QZGNVDQ","short_pith_number":"pith:LTT5MXV6","schema_version":"1.0","canonical_sha256":"5ce7d65ebe3cc5b5404e903f0c99b51c2604b3004dd6766f1063bbd96dcb7540","source":{"kind":"arxiv","id":"1802.09640","version":3},"attestation_state":"computed","paper":{"title":"Modeling Others using Oneself in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Arthur Szlam, Emily Denton, Roberta Raileanu, Rob Fergus","submitted_at":"2018-02-26T23:27:53Z","abstract_excerpt":"We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three differe"},"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":"1802.09640","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-26T23:27:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2b70ae7a1297ef304ec06c2e3b350fd80a1f5dc51f165aa1dd6c540534df96ef","abstract_canon_sha256":"010624116b7483c913934b4358233327e2117dff8faf4116c3d43a5288a233f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:13.554492Z","signature_b64":"45BSihLejyTSVcgsVRlzDdfB78Iq+2ueI3TziDHdI0xcMfImDwcux5NaxdPRYFIw97q62R+vNtxqLghiI3GUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce7d65ebe3cc5b5404e903f0c99b51c2604b3004dd6766f1063bbd96dcb7540","last_reissued_at":"2026-05-18T00:20:13.553973Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:13.553973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Others using Oneself in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Arthur Szlam, Emily Denton, Roberta Raileanu, Rob Fergus","submitted_at":"2018-02-26T23:27:53Z","abstract_excerpt":"We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09640","kind":"arxiv","version":3},"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":"1802.09640","created_at":"2026-05-18T00:20:13.554046+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09640v3","created_at":"2026-05-18T00:20:13.554046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09640","created_at":"2026-05-18T00:20:13.554046+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTT5MXV6HTC3","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTT5MXV6HTC3KQCO","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTT5MXV6","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10918","citing_title":"Towards Empathic Deep Q-Learning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ","json":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ.json","graph_json":"https://pith.science/api/pith-number/LTT5MXV6HTC3KQCOSA7QZGNVDQ/graph.json","events_json":"https://pith.science/api/pith-number/LTT5MXV6HTC3KQCOSA7QZGNVDQ/events.json","paper":"https://pith.science/paper/LTT5MXV6"},"agent_actions":{"view_html":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ","download_json":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ.json","view_paper":"https://pith.science/paper/LTT5MXV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09640&json=true","fetch_graph":"https://pith.science/api/pith-number/LTT5MXV6HTC3KQCOSA7QZGNVDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LTT5MXV6HTC3KQCOSA7QZGNVDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ/action/storage_attestation","attest_author":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ/action/author_attestation","sign_citation":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ/action/citation_signature","submit_replication":"https://pith.science/pith/LTT5MXV6HTC3KQCOSA7QZGNVDQ/action/replication_record"}},"created_at":"2026-05-18T00:20:13.554046+00:00","updated_at":"2026-05-18T00:20:13.554046+00:00"}