{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2TRPT4VLWBEDOJ7FJ4OT57ZA3I","short_pith_number":"pith:2TRPT4VL","schema_version":"1.0","canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","source":{"kind":"arxiv","id":"2203.02481","version":1},"attestation_state":"computed","paper":{"title":"AutoDIME: Automatic Design of Interesting Multi-Agent Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harri Edwards, Ingmar Kanitscheider","submitted_at":"2022-03-04T18:25:33Z","abstract_excerpt":"Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a second RL agent, called a teacher, who samples environments that are conducive for the learning of student agents. However, most previous proposals for teacher rewards do not generalize straightforwardly to the multi-agent setting. We examine a set of intrinsic teacher rewards derived from prediction problems that can be applied in multi-agent settings and e"},"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":"2203.02481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"39a0e858b5ff09e09db83ad7a110365ea311606b75cd2441ee048ffe98b2a8f1","abstract_canon_sha256":"4fa8830b7767fd4bc988f20089afa748d8c36d89295920bde34c14eb25f710d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:11.081557Z","signature_b64":"HRXfDr7MKO6kl830/U1e7gB1HbpxivFPJlByHCqKbHYfWUofQwC888nqMGlTOyC87pb/TPDeWhy85YbzT1wTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","last_reissued_at":"2026-07-05T04:02:11.080958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:11.080958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoDIME: Automatic Design of Interesting Multi-Agent Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harri Edwards, Ingmar Kanitscheider","submitted_at":"2022-03-04T18:25:33Z","abstract_excerpt":"Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a second RL agent, called a teacher, who samples environments that are conducive for the learning of student agents. However, most previous proposals for teacher rewards do not generalize straightforwardly to the multi-agent setting. We examine a set of intrinsic teacher rewards derived from prediction problems that can be applied in multi-agent settings and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02481","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/2203.02481/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":"2203.02481","created_at":"2026-07-05T04:02:11.081013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02481v1","created_at":"2026-07-05T04:02:11.081013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02481","created_at":"2026-07-05T04:02:11.081013+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TRPT4VLWBED","created_at":"2026-07-05T04:02:11.081013+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TRPT4VLWBEDOJ7F","created_at":"2026-07-05T04:02:11.081013+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TRPT4VL","created_at":"2026-07-05T04:02:11.081013+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/2TRPT4VLWBEDOJ7FJ4OT57ZA3I","json":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I.json","graph_json":"https://pith.science/api/pith-number/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/graph.json","events_json":"https://pith.science/api/pith-number/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/events.json","paper":"https://pith.science/paper/2TRPT4VL"},"agent_actions":{"view_html":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I","download_json":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I.json","view_paper":"https://pith.science/paper/2TRPT4VL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02481&json=true","fetch_graph":"https://pith.science/api/pith-number/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/graph.json","fetch_events":"https://pith.science/api/pith-number/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/action/storage_attestation","attest_author":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/action/author_attestation","sign_citation":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/action/citation_signature","submit_replication":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/action/replication_record"}},"created_at":"2026-07-05T04:02:11.081013+00:00","updated_at":"2026-07-05T04:02:11.081013+00:00"}