{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IMC3TUN6EI3O3PTHCZ6WYIZBY6","short_pith_number":"pith:IMC3TUN6","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"},"canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","source":{"kind":"arxiv","id":"2207.05631","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05631","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05631v3","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05631","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"IMC3TUN6EI3O","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"IMC3TUN6EI3O3PTH","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"IMC3TUN6","created_at":"2026-07-05T07:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IMC3TUN6EI3O3PTHCZ6WYIZBY6","target":"record","payload":{"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"},"canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","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"},"source_kind":"arxiv","source_id":"2207.05631","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P3mN/C7aaQNaXKbfyAz9EqKFgEevvyoMc5df5SF1hp0qBzTto14b1RX6AiVZFLoJ/QgzCkpHk5rMYeHJfeYGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:38:42.108642Z"},"content_sha256":"e384a777d81a61a1b1c8614a93532bb4d4d1a09f72817db57e264ce83fd77df2","schema_version":"1.0","event_id":"sha256:e384a777d81a61a1b1c8614a93532bb4d4d1a09f72817db57e264ce83fd77df2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IMC3TUN6EI3O3PTHCZ6WYIZBY6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FE+4bcI/rLUCgFjhH79i+kMSoV7WwPkMGMAVEfGWCphkd4S8LoCgPVRo31YTAluFp33fBUdg8GkAslT0o0NwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:38:42.109164Z"},"content_sha256":"866065945742955007613b453f4062cea92e7d20c66119473c2dba283f62e912","schema_version":"1.0","event_id":"sha256:866065945742955007613b453f4062cea92e7d20c66119473c2dba283f62e912"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/bundle.json","state_url":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T08:38:42Z","links":{"resolver":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6","bundle":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/bundle.json","state":"https://pith.science/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMC3TUN6EI3O3PTHCZ6WYIZBY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IMC3TUN6EI3O3PTHCZ6WYIZBY6","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":"99a67319ecea3b6aae92c532583ff78f726e20661c7dc08f40d80a67c81e1665","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T15:57:55Z","title_canon_sha256":"be24b7adf5b7b600574cb269516f4207fac4b0c1b30df13feb951169813d7ef9"},"schema_version":"1.0","source":{"id":"2207.05631","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05631","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05631v3","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05631","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"IMC3TUN6EI3O","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"IMC3TUN6EI3O3PTH","created_at":"2026-07-05T07:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"IMC3TUN6","created_at":"2026-07-05T07:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:866065945742955007613b453f4062cea92e7d20c66119473c2dba283f62e912","target":"graph","created_at":"2026-07-05T07:30:44Z","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/2207.05631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jun Zhu, Shiyu Huang, Tim Pearce, Ting Chen, Wei-Wei Tu, Wentse Chen, Yuan Chiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T15:57:55Z","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05631","kind":"arxiv","version":3},"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:e384a777d81a61a1b1c8614a93532bb4d4d1a09f72817db57e264ce83fd77df2","target":"record","created_at":"2026-07-05T07:30:44Z","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":"99a67319ecea3b6aae92c532583ff78f726e20661c7dc08f40d80a67c81e1665","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T15:57:55Z","title_canon_sha256":"be24b7adf5b7b600574cb269516f4207fac4b0c1b30df13feb951169813d7ef9"},"schema_version":"1.0","source":{"id":"2207.05631","kind":"arxiv","version":3}},"canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4305b9d1be2236edbe67167d6c2321c7a3070c73b16dc8e2eead9b6c33533ea9","first_computed_at":"2026-07-05T07:30:44.033994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:44.033994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44colG0rVU9y5uiHv/ixwFOc3S/HcGzLL1GcdFz9d9tkb0BuZJ8wZGglFuYMeXcqG8VCAY5NqStTuDYH2uhPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:44.034514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.05631","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e384a777d81a61a1b1c8614a93532bb4d4d1a09f72817db57e264ce83fd77df2","sha256:866065945742955007613b453f4062cea92e7d20c66119473c2dba283f62e912"],"state_sha256":"7b9ee32f63dc2a57e609565801253976c5135ab82d57a3d3097cb8e638797b10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8sHbzhmIOJ9tzCMi8lktyLjAH/3L++bx1huJUF2DZMm7v4LN2DiJPi9TYuq5Zrs0nTd/HioGtCSIzwY/QBWBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:38:42.113913Z","bundle_sha256":"b4eaa1772301c3a5bc2edfde6fe6051afd5a450df3d10ef638de3e1ceea59eea"}}