{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P24KUMEOHSDWV74Y42N3PF7SOK","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":"0c1e8f2c330330fc1949c4ca255d7e4e57c1727439e1a98c6abda198d7ee6702","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T19:55:42Z","title_canon_sha256":"82d91262ae2118f31d73b13a236252aacba6d81a8367bd29bd79e1b3a73a5ebf"},"schema_version":"1.0","source":{"id":"2210.01801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01801","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01801v1","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01801","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"P24KUMEOHSDW","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"P24KUMEOHSDWV74Y","created_at":"2026-07-05T05:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"P24KUMEO","created_at":"2026-07-05T05:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:448eb19374c75caec9967703b7709217fc63ef5ab6f06a98d1d65adf2c55d57f","target":"graph","created_at":"2026-07-05T05:03:40Z","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/2210.01801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3) high-dimensional observations. We formalize the problem in a constrained, partially observable Markov decision process framework, where an agent obtains distinct reward and safety signals. To address the curse of dimensionality, we employ a novel safety critic using the stochastic latent actor-critic (SLAC) approach. The latent variable model predicts rewards and","authors_text":"Nils Jansen, Tal Kachman, Thiago D. Simao, Yannick Hogewind","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T19:55:42Z","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01801","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:bfbb26af699ef35a95ab10b8943a7be2729278ddddaac2e59586b68e7c6c7b80","target":"record","created_at":"2026-07-05T05:03:40Z","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":"0c1e8f2c330330fc1949c4ca255d7e4e57c1727439e1a98c6abda198d7ee6702","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T19:55:42Z","title_canon_sha256":"82d91262ae2118f31d73b13a236252aacba6d81a8367bd29bd79e1b3a73a5ebf"},"schema_version":"1.0","source":{"id":"2210.01801","kind":"arxiv","version":1}},"canonical_sha256":"7eb8aa308e3c876aff98e69bb797f272b372588418aac94e31d149f1b772c4e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eb8aa308e3c876aff98e69bb797f272b372588418aac94e31d149f1b772c4e6","first_computed_at":"2026-07-05T05:03:40.279326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:40.279326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"77wo+lCZ/LRBeD/VtQmt3eUJDTC0Qd9MS31OGkC73pF+Cw0+kRWJPU2o9A64uTSkVyMI94PNMphja0XGfG46Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:40.279750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfbb26af699ef35a95ab10b8943a7be2729278ddddaac2e59586b68e7c6c7b80","sha256:448eb19374c75caec9967703b7709217fc63ef5ab6f06a98d1d65adf2c55d57f"],"state_sha256":"04c7604b70c4a2d2e74a474e94248c1aa187c2ce2291d7830ff6f954a597f16b"}