{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DIQMCOLSY2XCAPCTYEJ45E3LIB","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":"57436483a34ef89f02bcd5da2cac621757c42c82c0890aa4ad79c19c4c30485d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-03-28T21:17:36Z","title_canon_sha256":"ed260b940eec0b577a7add7c6eb75f18d8c9b7a055d4dbcab4a5921cc6b0bda3"},"schema_version":"1.0","source":{"id":"2203.15103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15103","created_at":"2026-07-05T04:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15103v1","created_at":"2026-07-05T04:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15103","created_at":"2026-07-05T04:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"DIQMCOLSY2XC","created_at":"2026-07-05T04:09:21Z"},{"alias_kind":"pith_short_16","alias_value":"DIQMCOLSY2XCAPCT","created_at":"2026-07-05T04:09:21Z"},{"alias_kind":"pith_short_8","alias_value":"DIQMCOLS","created_at":"2026-07-05T04:09:21Z"}],"graph_snapshots":[{"event_id":"sha256:2da6f7b09430a3a5e7ceefc34e8f4bb1b1b1da3aca12a60b7e9903e022511e93","target":"graph","created_at":"2026-07-05T04:09:21Z","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/2203.15103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors, reinforcement learning practitioners often utilize complex reward functions that encourage physically plausible behaviors. However, a tedious labor-intensive tuning process is often required to create hand-designed rewards which might not easily generalize across platforms and tasks. We propose substituting complex reward functions with \"style rewards\" lear","authors_text":"Alejandro Escontrela, Atil Iscen, Ken Goldberg, Pieter Abbeel, Tingnan Zhang, Wenhao Yu, Xue Bin Peng","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-03-28T21:17:36Z","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15103","kind":"arxiv","version":1},"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":"sha256:350be32fa8964ecd85b7eb4143c83a898b13dbdad81b8cd405a5a92fbf2da7ab","target":"record","created_at":"2026-07-05T04:09:21Z","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":"57436483a34ef89f02bcd5da2cac621757c42c82c0890aa4ad79c19c4c30485d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-03-28T21:17:36Z","title_canon_sha256":"ed260b940eec0b577a7add7c6eb75f18d8c9b7a055d4dbcab4a5921cc6b0bda3"},"schema_version":"1.0","source":{"id":"2203.15103","kind":"arxiv","version":1}},"canonical_sha256":"1a20c13972c6ae203c53c113ce936b407e752966e5ce08aeea9d025d0357f993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a20c13972c6ae203c53c113ce936b407e752966e5ce08aeea9d025d0357f993","first_computed_at":"2026-07-05T04:09:21.609353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:21.609353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HRcC5Baqqoju6s5NUdV40bMNUDfzqcqICmXObrk2it8pb7gj670Fq+ihav1icnZwR3+kbtfRb4/eMj8H5zOVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:21.609754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:350be32fa8964ecd85b7eb4143c83a898b13dbdad81b8cd405a5a92fbf2da7ab","sha256:2da6f7b09430a3a5e7ceefc34e8f4bb1b1b1da3aca12a60b7e9903e022511e93"],"state_sha256":"4a88ecfedb220963da623b9c5d58db90a834f2b716c2a2a39985185efaedb83f"}