{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MQ2C7ZZ4NDXSGND3VF5H7NDF45","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":"9630fcad6779e3e7e1012ed97992e8052e1c036d0aa3067d5c6514b298766221","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T17:47:03Z","title_canon_sha256":"84ce245183c15cac7c9b2aa9bbdcee60ab42ba0b508f0190028cb443ccdb79bf"},"schema_version":"1.0","source":{"id":"2407.02466","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02466","created_at":"2026-07-05T10:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02466v3","created_at":"2026-07-05T10:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02466","created_at":"2026-07-05T10:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"MQ2C7ZZ4NDXS","created_at":"2026-07-05T10:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"MQ2C7ZZ4NDXSGND3","created_at":"2026-07-05T10:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"MQ2C7ZZ4","created_at":"2026-07-05T10:18:39Z"}],"graph_snapshots":[{"event_id":"sha256:4aa5eecb4891fa3b79bac11aaed2a375c0b9cb36bc814d75fe1d10c3fa92fa64","target":"graph","created_at":"2026-07-05T10:18:39Z","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/2407.02466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has made significant strides in complex tasks but struggles in multi-task settings with different embodiments. World model methods offer scalability by learning a simulation of the environment but often rely on inefficient gradient-free optimization methods for policy extraction. In contrast, gradient-based methods exhibit lower variance but fail to handle discontinuities. Our work reveals that well-regularized world models can generate smoother optimization landscapes than the actual dynamics, facilitating more effective first-order optimization. We introduce Polic","authors_text":"Animesh Garg, Ignat Georgiev, Nicklas Hansen, Varun Giridhar","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T17:47:03Z","title":"PWM: Policy Learning with Multi-Task World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02466","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":"sha256:01dea8f3590971e1f3f36224890e9aaae9d4cff20a9aca1cb0ade995a4055cdf","target":"record","created_at":"2026-07-05T10:18:39Z","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":"9630fcad6779e3e7e1012ed97992e8052e1c036d0aa3067d5c6514b298766221","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-02T17:47:03Z","title_canon_sha256":"84ce245183c15cac7c9b2aa9bbdcee60ab42ba0b508f0190028cb443ccdb79bf"},"schema_version":"1.0","source":{"id":"2407.02466","kind":"arxiv","version":3}},"canonical_sha256":"64342fe73c68ef23347ba97a7fb465e7775deec22d953e2b850489a75cbe36de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64342fe73c68ef23347ba97a7fb465e7775deec22d953e2b850489a75cbe36de","first_computed_at":"2026-07-05T10:18:39.165149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:39.165149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wh8DEW1elOoRRVs/en+lNz5ayCHpaJcMNoSfLNaRnot9zn/PPymvbqXeVzMrMfZ8osgqkyLIWL3nPTJQ/iu8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:39.165705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02466","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01dea8f3590971e1f3f36224890e9aaae9d4cff20a9aca1cb0ade995a4055cdf","sha256:4aa5eecb4891fa3b79bac11aaed2a375c0b9cb36bc814d75fe1d10c3fa92fa64"],"state_sha256":"2a202a640586ffb7695232e7d261f43f216a00844a1022542fd6834c92fd084e"}