{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QVH43KDVZK23AMNMTMM6HWDMQS","short_pith_number":"pith:QVH43KDV","schema_version":"1.0","canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","source":{"kind":"arxiv","id":"2307.14316","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning by Guided Safe Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Nils Jansen, Qisong Yang, Simon H. Tindemans, Thiago D. Sim\\~ao","submitted_at":"2023-07-26T17:26:21Z","abstract_excerpt":"Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once the reward is revealed. We consider the constrained reward-free setting, where an agent (the guide) learns to explore safely without the reward signal. This agent is trained in a controlled environment, which allows unsafe interactions and still provides "},"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":"2307.14316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43d08f2673aac69d2ae3ef17942ad929e89818f44c1c13dfc14e2cf8e39adf2a","abstract_canon_sha256":"8499d7e036792b588725c9c02045e83c6b49f9f11a96b47423d3a20e70ef27b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:03.131509Z","signature_b64":"KMSyMzFVHWyw7ErcycrRBAzq8vk+U6mHLEsJjb69n5uM3TdAya8e4Cd2QpZdXvFFmodMKtt+hPJN9mT6UVZFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","last_reissued_at":"2026-07-05T07:59:03.131008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:03.131008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning by Guided Safe Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Nils Jansen, Qisong Yang, Simon H. Tindemans, Thiago D. Sim\\~ao","submitted_at":"2023-07-26T17:26:21Z","abstract_excerpt":"Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once the reward is revealed. We consider the constrained reward-free setting, where an agent (the guide) learns to explore safely without the reward signal. This agent is trained in a controlled environment, which allows unsafe interactions and still provides "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14316","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/2307.14316/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":"2307.14316","created_at":"2026-07-05T07:59:03.131069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14316v1","created_at":"2026-07-05T07:59:03.131069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14316","created_at":"2026-07-05T07:59:03.131069+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVH43KDVZK23","created_at":"2026-07-05T07:59:03.131069+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVH43KDVZK23AMNM","created_at":"2026-07-05T07:59:03.131069+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVH43KDV","created_at":"2026-07-05T07:59:03.131069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14375","citing_title":"Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS","json":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS.json","graph_json":"https://pith.science/api/pith-number/QVH43KDVZK23AMNMTMM6HWDMQS/graph.json","events_json":"https://pith.science/api/pith-number/QVH43KDVZK23AMNMTMM6HWDMQS/events.json","paper":"https://pith.science/paper/QVH43KDV"},"agent_actions":{"view_html":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS","download_json":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS.json","view_paper":"https://pith.science/paper/QVH43KDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14316&json=true","fetch_graph":"https://pith.science/api/pith-number/QVH43KDVZK23AMNMTMM6HWDMQS/graph.json","fetch_events":"https://pith.science/api/pith-number/QVH43KDVZK23AMNMTMM6HWDMQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/action/storage_attestation","attest_author":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/action/author_attestation","sign_citation":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/action/citation_signature","submit_replication":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/action/replication_record"}},"created_at":"2026-07-05T07:59:03.131069+00:00","updated_at":"2026-07-05T07:59:03.131069+00:00"}