{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZLSPF2SXOEFZ5FFICSXKCIBTZX","short_pith_number":"pith:ZLSPF2SX","schema_version":"1.0","canonical_sha256":"cae4f2ea57710b9e94a814aea12033cdf5ee123adad6d084a16ca3a5f200905e","source":{"kind":"arxiv","id":"2111.11692","version":1},"attestation_state":"computed","paper":{"title":"Status-quo policy gradient in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Abhishek Sinha, Balaji Krishnamurthy, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Pinkesh Badjatiya, Siddharth Singh","submitted_at":"2021-11-23T07:22:05Z","abstract_excerpt":"Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group outcomes in multi-agent problems. For instance, in multi-agent social dilemmas, Reinforcement Learning (RL) agents trained to maximize individual rewards converge to a low-utility mutually harmful equilibrium. In contrast, humans evolve useful strategies in such social dilemmas. Inspired by ideas from human psychology that attribute this behavior to the status-quo bias, we present a status-quo loss (SQLoss) and the corresponding policy gradient algorithm that "},"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":"2111.11692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-11-23T07:22:05Z","cross_cats_sorted":[],"title_canon_sha256":"1969109b9e545e757ea2888846c66fb3dee1ef1cb6c1ffce3965056417aba8cf","abstract_canon_sha256":"6eab0d87eaacf8ba8026c7a2d82b9a1abec45e92628744cf8781fde9abbbdea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:11.793184Z","signature_b64":"vRAN49stNJXCbNRJt43jS60OZ+rv4pz1icoPRmAQtKEnnS6bEd28SV/101PYs4KCx09tueDtpCCtsyrFl0VcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cae4f2ea57710b9e94a814aea12033cdf5ee123adad6d084a16ca3a5f200905e","last_reissued_at":"2026-07-05T03:34:11.792756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:11.792756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Status-quo policy gradient in Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Abhishek Sinha, Balaji Krishnamurthy, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Pinkesh Badjatiya, Siddharth Singh","submitted_at":"2021-11-23T07:22:05Z","abstract_excerpt":"Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group outcomes in multi-agent problems. For instance, in multi-agent social dilemmas, Reinforcement Learning (RL) agents trained to maximize individual rewards converge to a low-utility mutually harmful equilibrium. In contrast, humans evolve useful strategies in such social dilemmas. Inspired by ideas from human psychology that attribute this behavior to the status-quo bias, we present a status-quo loss (SQLoss) and the corresponding policy gradient algorithm that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11692","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.11692/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":"2111.11692","created_at":"2026-07-05T03:34:11.792824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11692v1","created_at":"2026-07-05T03:34:11.792824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11692","created_at":"2026-07-05T03:34:11.792824+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLSPF2SXOEFZ","created_at":"2026-07-05T03:34:11.792824+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLSPF2SXOEFZ5FFI","created_at":"2026-07-05T03:34:11.792824+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLSPF2SX","created_at":"2026-07-05T03:34:11.792824+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/ZLSPF2SXOEFZ5FFICSXKCIBTZX","json":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX.json","graph_json":"https://pith.science/api/pith-number/ZLSPF2SXOEFZ5FFICSXKCIBTZX/graph.json","events_json":"https://pith.science/api/pith-number/ZLSPF2SXOEFZ5FFICSXKCIBTZX/events.json","paper":"https://pith.science/paper/ZLSPF2SX"},"agent_actions":{"view_html":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX","download_json":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX.json","view_paper":"https://pith.science/paper/ZLSPF2SX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11692&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLSPF2SXOEFZ5FFICSXKCIBTZX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLSPF2SXOEFZ5FFICSXKCIBTZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX/action/storage_attestation","attest_author":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX/action/author_attestation","sign_citation":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX/action/citation_signature","submit_replication":"https://pith.science/pith/ZLSPF2SXOEFZ5FFICSXKCIBTZX/action/replication_record"}},"created_at":"2026-07-05T03:34:11.792824+00:00","updated_at":"2026-07-05T03:34:11.792824+00:00"}