{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KM6SW7T4LSRMO2R4W7NKLB7GRT","short_pith_number":"pith:KM6SW7T4","schema_version":"1.0","canonical_sha256":"533d2b7e7c5ca2c76a3cb7daa587e68cc4a083fe62a7d56a1a0bb3194961046b","source":{"kind":"arxiv","id":"2005.03233","version":1},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning through Meta-learned Instincts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Djordje Grbic, Sebastian Risi","submitted_at":"2020-05-06T17:31:53Z","abstract_excerpt":"An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies. However, in deep reinforcement learning, exploration is normally done by injecting noise in the action space. While performing well in many domains, this setup has the inherent risk that the noisy actions performed by the agent lead to unsafe states in the environment. Here we introduce a novel approach called Me"},"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":"2005.03233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-06T17:31:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f49f2cca2e5b0b4c69675d059662700b05daf76f89e7a49a8a35e0f6d2c4e3d","abstract_canon_sha256":"833086338cb7139c3032c4fcd63c6cc82486ee7eeaba5800767e8f3486eb9d4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:06.445486Z","signature_b64":"CUFL1grTSLw4kSblEVVwK9UHkSDhoYvpuoJ9sK4kPBrc9ZjsGQvq2lfYBtRdfmMlfiXqWwPAdU213NH6d8EnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"533d2b7e7c5ca2c76a3cb7daa587e68cc4a083fe62a7d56a1a0bb3194961046b","last_reissued_at":"2026-07-05T01:01:06.444952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:06.444952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning through Meta-learned Instincts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Djordje Grbic, Sebastian Risi","submitted_at":"2020-05-06T17:31:53Z","abstract_excerpt":"An important goal in reinforcement learning is to create agents that can quickly adapt to new goals while avoiding situations that might cause damage to themselves or their environments. One way agents learn is through exploration mechanisms, which are needed to discover new policies. However, in deep reinforcement learning, exploration is normally done by injecting noise in the action space. While performing well in many domains, this setup has the inherent risk that the noisy actions performed by the agent lead to unsafe states in the environment. Here we introduce a novel approach called Me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03233","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/2005.03233/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":"2005.03233","created_at":"2026-07-05T01:01:06.445024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.03233v1","created_at":"2026-07-05T01:01:06.445024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03233","created_at":"2026-07-05T01:01:06.445024+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM6SW7T4LSRM","created_at":"2026-07-05T01:01:06.445024+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM6SW7T4LSRMO2R4","created_at":"2026-07-05T01:01:06.445024+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM6SW7T4","created_at":"2026-07-05T01:01:06.445024+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/KM6SW7T4LSRMO2R4W7NKLB7GRT","json":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT.json","graph_json":"https://pith.science/api/pith-number/KM6SW7T4LSRMO2R4W7NKLB7GRT/graph.json","events_json":"https://pith.science/api/pith-number/KM6SW7T4LSRMO2R4W7NKLB7GRT/events.json","paper":"https://pith.science/paper/KM6SW7T4"},"agent_actions":{"view_html":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT","download_json":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT.json","view_paper":"https://pith.science/paper/KM6SW7T4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.03233&json=true","fetch_graph":"https://pith.science/api/pith-number/KM6SW7T4LSRMO2R4W7NKLB7GRT/graph.json","fetch_events":"https://pith.science/api/pith-number/KM6SW7T4LSRMO2R4W7NKLB7GRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT/action/storage_attestation","attest_author":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT/action/author_attestation","sign_citation":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT/action/citation_signature","submit_replication":"https://pith.science/pith/KM6SW7T4LSRMO2R4W7NKLB7GRT/action/replication_record"}},"created_at":"2026-07-05T01:01:06.445024+00:00","updated_at":"2026-07-05T01:01:06.445024+00:00"}