{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P24KUMEOHSDWV74Y42N3PF7SOK","short_pith_number":"pith:P24KUMEO","schema_version":"1.0","canonical_sha256":"7eb8aa308e3c876aff98e69bb797f272b372588418aac94e31d149f1b772c4e6","source":{"kind":"arxiv","id":"2210.01801","version":1},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nils Jansen, Tal Kachman, Thiago D. Simao, Yannick Hogewind","submitted_at":"2022-10-02T19:55:42Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.01801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T19:55:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82d91262ae2118f31d73b13a236252aacba6d81a8367bd29bd79e1b3a73a5ebf","abstract_canon_sha256":"0c1e8f2c330330fc1949c4ca255d7e4e57c1727439e1a98c6abda198d7ee6702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:40.279750Z","signature_b64":"77wo+lCZ/LRBeD/VtQmt3eUJDTC0Qd9MS31OGkC73pF+Cw0+kRWJPU2o9A64uTSkVyMI94PNMphja0XGfG46Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb8aa308e3c876aff98e69bb797f272b372588418aac94e31d149f1b772c4e6","last_reissued_at":"2026-07-05T05:03:40.279326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:40.279326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nils Jansen, Tal Kachman, Thiago D. Simao, Yannick Hogewind","submitted_at":"2022-10-02T19:55:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01801","kind":"arxiv","version":1},"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/2210.01801/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.01801","created_at":"2026-07-05T05:03:40.279389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01801v1","created_at":"2026-07-05T05:03:40.279389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01801","created_at":"2026-07-05T05:03:40.279389+00:00"},{"alias_kind":"pith_short_12","alias_value":"P24KUMEOHSDW","created_at":"2026-07-05T05:03:40.279389+00:00"},{"alias_kind":"pith_short_16","alias_value":"P24KUMEOHSDWV74Y","created_at":"2026-07-05T05:03:40.279389+00:00"},{"alias_kind":"pith_short_8","alias_value":"P24KUMEO","created_at":"2026-07-05T05:03:40.279389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK","json":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK.json","graph_json":"https://pith.science/api/pith-number/P24KUMEOHSDWV74Y42N3PF7SOK/graph.json","events_json":"https://pith.science/api/pith-number/P24KUMEOHSDWV74Y42N3PF7SOK/events.json","paper":"https://pith.science/paper/P24KUMEO"},"agent_actions":{"view_html":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK","download_json":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK.json","view_paper":"https://pith.science/paper/P24KUMEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01801&json=true","fetch_graph":"https://pith.science/api/pith-number/P24KUMEOHSDWV74Y42N3PF7SOK/graph.json","fetch_events":"https://pith.science/api/pith-number/P24KUMEOHSDWV74Y42N3PF7SOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK/action/storage_attestation","attest_author":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK/action/author_attestation","sign_citation":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK/action/citation_signature","submit_replication":"https://pith.science/pith/P24KUMEOHSDWV74Y42N3PF7SOK/action/replication_record"}},"created_at":"2026-07-05T05:03:40.279389+00:00","updated_at":"2026-07-05T05:03:40.279389+00:00"}