{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6STSFLAKMJG23X6ZXDTHK6DM76","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":"92392c227d1699236143ecf4261c1f2bee0e4303e57e7b27900e9a81619e4aa0","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-20T18:16:21Z","title_canon_sha256":"464baefdc91631ccf16650910882b7c49e3391f98db49022ebf67294711ffd59"},"schema_version":"1.0","source":{"id":"2104.10190","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10190","created_at":"2026-07-05T05:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10190v2","created_at":"2026-07-05T05:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10190","created_at":"2026-07-05T05:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"6STSFLAKMJG2","created_at":"2026-07-05T05:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"6STSFLAKMJG23X6Z","created_at":"2026-07-05T05:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"6STSFLAK","created_at":"2026-07-05T05:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:7a6efdf685e64ffec7c25f844108e9fa798788c09001054d10e2e4dacfd54562","target":"graph","created_at":"2026-07-05T05:28:41Z","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/2104.10190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the task, but also provide sufficient shaping to accomplish it. In this paper, we view reinforcement learning as inferring policies that achieve desired outcomes, rather than as a problem of maximizing rewards. To solve this inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function which can be ","authors_text":"Rowan McAllister, Sergey Levine, Tim G. J. Rudner, Vitchyr H. Pong, Yarin Gal","cross_cats":["cs.AI","stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-20T18:16:21Z","title":"Outcome-Driven Reinforcement Learning via Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10190","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":"sha256:102db00ed69f705c5d577f84ab338cfa89748b64aa643cc855b2fb81e7bd70fc","target":"record","created_at":"2026-07-05T05:28:41Z","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":"92392c227d1699236143ecf4261c1f2bee0e4303e57e7b27900e9a81619e4aa0","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-20T18:16:21Z","title_canon_sha256":"464baefdc91631ccf16650910882b7c49e3391f98db49022ebf67294711ffd59"},"schema_version":"1.0","source":{"id":"2104.10190","kind":"arxiv","version":2}},"canonical_sha256":"f4a722ac0a624daddfd9b8e675786cffa1009ebf694cb6cd4b85609229ffad10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4a722ac0a624daddfd9b8e675786cffa1009ebf694cb6cd4b85609229ffad10","first_computed_at":"2026-07-05T05:28:41.746666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:41.746666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"THFVtqWf+70+z1XCImbo5x033/COcILjRBtqPrFB+3Cko00ulvbNPVj+uLoNwq6E9na+9RZ6KuhL9r8JniI+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:41.747101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.10190","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:102db00ed69f705c5d577f84ab338cfa89748b64aa643cc855b2fb81e7bd70fc","sha256:7a6efdf685e64ffec7c25f844108e9fa798788c09001054d10e2e4dacfd54562"],"state_sha256":"94416566357fb35e0c3fbfd819ae906d4fcc044daef12e816c5d5897e4ce2a30"}