{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QHUZUH7LSVTO2EL7UNZHS76VYK","short_pith_number":"pith:QHUZUH7L","schema_version":"1.0","canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","source":{"kind":"arxiv","id":"1709.02865","version":2},"attestation_state":"computed","paper":{"title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Alexander Peysakhovich","submitted_at":"2017-09-08T21:52:58Z","abstract_excerpt":"Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner's environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choo"},"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":"1709.02865","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-08T21:52:58Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"b9ca3a3d6036779ed980eb5dceddbc6321f7d2e4cfaa8ed96d8b544eb50d5a3a","abstract_canon_sha256":"0f8d18d449a2adda8e778355f60d3574f6821d9d1a81cd2bf0f4027fc0a3f7e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:29.677909Z","signature_b64":"OiwTJpaKrfJz6/YrtgpDGrYNDG+JVlGfERNEysLww2SjzdtWmLeKH6fxyfnCTxjLTECBB0XeQ/VvDxO5Aa63AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e99a1feb9566ed117fa372797fd5c2aff38ceb2b4c24f61d79f3a36e42f1d2","last_reissued_at":"2026-05-18T00:28:29.677160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:29.677160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Alexander Peysakhovich","submitted_at":"2017-09-08T21:52:58Z","abstract_excerpt":"Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner's environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02865","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":"1709.02865","created_at":"2026-05-18T00:28:29.677279+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02865v2","created_at":"2026-05-18T00:28:29.677279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02865","created_at":"2026-05-18T00:28:29.677279+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHUZUH7LSVTO","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHUZUH7LSVTO2EL7","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHUZUH7L","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03818","citing_title":"Investigating the Impact of Subgraph Social Structure Preference on the Strategic Behavior of Networked Mixed-Motive Learning Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15695","citing_title":"The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK","json":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK.json","graph_json":"https://pith.science/api/pith-number/QHUZUH7LSVTO2EL7UNZHS76VYK/graph.json","events_json":"https://pith.science/api/pith-number/QHUZUH7LSVTO2EL7UNZHS76VYK/events.json","paper":"https://pith.science/paper/QHUZUH7L"},"agent_actions":{"view_html":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK","download_json":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK.json","view_paper":"https://pith.science/paper/QHUZUH7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02865&json=true","fetch_graph":"https://pith.science/api/pith-number/QHUZUH7LSVTO2EL7UNZHS76VYK/graph.json","fetch_events":"https://pith.science/api/pith-number/QHUZUH7LSVTO2EL7UNZHS76VYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/action/storage_attestation","attest_author":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/action/author_attestation","sign_citation":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/action/citation_signature","submit_replication":"https://pith.science/pith/QHUZUH7LSVTO2EL7UNZHS76VYK/action/replication_record"}},"created_at":"2026-05-18T00:28:29.677279+00:00","updated_at":"2026-05-18T00:28:29.677279+00:00"}