{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IMC3TUN6EI3O3PTHCZ6WYIZBY6","short_pith_number":"pith:IMC3TUN6","schema_version":"1.0","canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","source":{"kind":"arxiv","id":"2207.05631","version":3},"attestation_state":"computed","paper":{"title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jun Zhu, Shiyu Huang, Tim Pearce, Ting Chen, Wei-Wei Tu, Wentse Chen, Yuan Chiang","submitted_at":"2022-07-12T15:57:55Z","abstract_excerpt":"Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or improve the robustness of a policy to an unexpected perturbance. We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task. Unlike prior work, it achieves this with a shared policy network trained over a single run. Specifically, we design an intrinsic reward based on an inform"},"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":"2207.05631","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T15:57:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be24b7adf5b7b600574cb269516f4207fac4b0c1b30df13feb951169813d7ef9","abstract_canon_sha256":"99a67319ecea3b6aae92c532583ff78f726e20661c7dc08f40d80a67c81e1665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:44.034514Z","signature_b64":"44colG0rVU9y5uiHv/ixwFOc3S/HcGzLL1GcdFz9d9tkb0BuZJ8wZGglFuYMeXcqG8VCAY5NqStTuDYH2uhPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","last_reissued_at":"2026-07-05T07:30:44.033994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:44.033994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jun Zhu, Shiyu Huang, Tim Pearce, Ting Chen, Wei-Wei Tu, Wentse Chen, Yuan Chiang","submitted_at":"2022-07-12T15:57:55Z","abstract_excerpt":"Most reinforcement learning algorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or improve the robustness of a policy to an unexpected perturbance. We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task. Unlike prior work, it achieves this with a shared policy network trained over a single run. Specifically, we design an intrinsic reward based on an inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05631","kind":"arxiv","version":3},"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/2207.05631/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":"2207.05631","created_at":"2026-07-05T07:30:44.034056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05631v3","created_at":"2026-07-05T07:30:44.034056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05631","created_at":"2026-07-05T07:30:44.034056+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMC3TUN6EI3O","created_at":"2026-07-05T07:30:44.034056+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMC3TUN6EI3O3PTH","created_at":"2026-07-05T07:30:44.034056+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMC3TUN6","created_at":"2026-07-05T07:30:44.034056+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/IMC3TUN6EI3O3PTHCZ6WYIZBY6","json":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6.json","graph_json":"https://pith.science/api/pith-number/IMC3TUN6EI3O3PTHCZ6WYIZBY6/graph.json","events_json":"https://pith.science/api/pith-number/IMC3TUN6EI3O3PTHCZ6WYIZBY6/events.json","paper":"https://pith.science/paper/IMC3TUN6"},"agent_actions":{"view_html":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6","download_json":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6.json","view_paper":"https://pith.science/paper/IMC3TUN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05631&json=true","fetch_graph":"https://pith.science/api/pith-number/IMC3TUN6EI3O3PTHCZ6WYIZBY6/graph.json","fetch_events":"https://pith.science/api/pith-number/IMC3TUN6EI3O3PTHCZ6WYIZBY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/action/storage_attestation","attest_author":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/action/author_attestation","sign_citation":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/action/citation_signature","submit_replication":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/action/replication_record"}},"created_at":"2026-07-05T07:30:44.034056+00:00","updated_at":"2026-07-05T07:30:44.034056+00:00"}