{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WB3NBGQYA66ZMYSAO2VXUKDYTW","short_pith_number":"pith:WB3NBGQY","schema_version":"1.0","canonical_sha256":"b076d09a1807bd96624076ab7a28789dabf246efb1ae583af59211734d35e49d","source":{"kind":"arxiv","id":"2006.06051","version":2},"attestation_state":"computed","paper":{"title":"Learning to Incentivize Other Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Edward Hughes, Hongyuan Zha, Jiachen Yang, Mehrdad Farajtabar, Peter Sunehag","submitted_at":"2020-06-10T20:12:38Z","abstract_excerpt":"The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined extrinsic reward function. However, a long-term question inevitably arises: how will such independent agents cooperate when they are continually learning and acting in a shared multi-agent environment? Observing that humans often provide incentives to influence others' behavior, we propose to equip each RL agent in a multi-agent environment with the ability to "},"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":"2006.06051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T20:12:38Z","cross_cats_sorted":["cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"d0f6698c7d82bde2d6c6a9cf0eccdd525e18a1684bb6e9d2cdb6c03a596103b5","abstract_canon_sha256":"56d11144e82c30c66c781bce9a5f6d9c5e63ea900142dff142419b92458d3443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:13.528311Z","signature_b64":"N3n2giqsPRNDSW5Rnnj/k9O66Xapq+KWHY6cI0d7monxf9FxuiSoDT1jTgzvvcJgbYn+bGMRcxPDo9EYhIYfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b076d09a1807bd96624076ab7a28789dabf246efb1ae583af59211734d35e49d","last_reissued_at":"2026-07-05T01:44:13.527900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:13.527900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Incentivize Other Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ang Li, Edward Hughes, Hongyuan Zha, Jiachen Yang, Mehrdad Farajtabar, Peter Sunehag","submitted_at":"2020-06-10T20:12:38Z","abstract_excerpt":"The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined extrinsic reward function. However, a long-term question inevitably arises: how will such independent agents cooperate when they are continually learning and acting in a shared multi-agent environment? Observing that humans often provide incentives to influence others' behavior, we propose to equip each RL agent in a multi-agent environment with the ability to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06051","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/2006.06051/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":"2006.06051","created_at":"2026-07-05T01:44:13.527956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06051v2","created_at":"2026-07-05T01:44:13.527956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06051","created_at":"2026-07-05T01:44:13.527956+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB3NBGQYA66Z","created_at":"2026-07-05T01:44:13.527956+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB3NBGQYA66ZMYSA","created_at":"2026-07-05T01:44:13.527956+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB3NBGQY","created_at":"2026-07-05T01:44:13.527956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09856","citing_title":"InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW","json":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW.json","graph_json":"https://pith.science/api/pith-number/WB3NBGQYA66ZMYSAO2VXUKDYTW/graph.json","events_json":"https://pith.science/api/pith-number/WB3NBGQYA66ZMYSAO2VXUKDYTW/events.json","paper":"https://pith.science/paper/WB3NBGQY"},"agent_actions":{"view_html":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW","download_json":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW.json","view_paper":"https://pith.science/paper/WB3NBGQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06051&json=true","fetch_graph":"https://pith.science/api/pith-number/WB3NBGQYA66ZMYSAO2VXUKDYTW/graph.json","fetch_events":"https://pith.science/api/pith-number/WB3NBGQYA66ZMYSAO2VXUKDYTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW/action/storage_attestation","attest_author":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW/action/author_attestation","sign_citation":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW/action/citation_signature","submit_replication":"https://pith.science/pith/WB3NBGQYA66ZMYSAO2VXUKDYTW/action/replication_record"}},"created_at":"2026-07-05T01:44:13.527956+00:00","updated_at":"2026-07-05T01:44:13.527956+00:00"}