{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HFXHGHZZ6UPI3ZUSFWDHKQQP2I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"047df6a37afc633d41a29710a05753dc6308c6736f86f5536273adfb6e15a117","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-26T17:40:52Z","title_canon_sha256":"a42c50e47ffad3d7003b771e610d73f1b85f6fbbf6b814855c5080ea2d506b1b"},"schema_version":"1.0","source":{"id":"2205.13521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13521","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13521v2","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13521","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"HFXHGHZZ6UPI","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"HFXHGHZZ6UPI3ZUS","created_at":"2026-07-05T05:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"HFXHGHZZ","created_at":"2026-07-05T05:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:0c61d1859858f69f01547519bf1ac6f760959df7ffa97f4c694667c80e823162","target":"graph","created_at":"2026-07-05T05:38:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.13521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, hierarchy, and robustness. We propose DOMiNO, a method for Diversity Optimization Maintaining Near Optimality. We formalize the problem as a Constrained Markov Decision Process where the objective is to find diverse policies, measured by the distance between the state occupancies of the policies in the set, while remaining near-optimal with respect to the extri","authors_text":"Feryal Behbahani, Kate Baumli, Satinder Singh, Sebastian Flennerhag, Shaobo Hou, Tom Zahavy, Yannick Schroecker","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-26T17:40:52Z","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13521","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fabb83d0bbb673e39ad2419adb9178bc6ed3137920007cbb6cbacdcda8e10368","target":"record","created_at":"2026-07-05T05:38:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"047df6a37afc633d41a29710a05753dc6308c6736f86f5536273adfb6e15a117","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-26T17:40:52Z","title_canon_sha256":"a42c50e47ffad3d7003b771e610d73f1b85f6fbbf6b814855c5080ea2d506b1b"},"schema_version":"1.0","source":{"id":"2205.13521","kind":"arxiv","version":2}},"canonical_sha256":"396e731f39f51e8de6922d8675420fd216625266059238c59ed3eae7b1de6c95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"396e731f39f51e8de6922d8675420fd216625266059238c59ed3eae7b1de6c95","first_computed_at":"2026-07-05T05:38:28.026280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:28.026280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bBsILoqA+KPClN/PM0IPYLDN9DKFlPa3/xYu4T8lpgaWIURtzNWkCuWdVmE57j7bdbEMYrBibICWMWvnfT0BDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:28.026716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fabb83d0bbb673e39ad2419adb9178bc6ed3137920007cbb6cbacdcda8e10368","sha256:0c61d1859858f69f01547519bf1ac6f760959df7ffa97f4c694667c80e823162"],"state_sha256":"89e8481331dfd0580051b6a0beaf44e12bbc3d7356e4645a67bb06c27a962160"}