{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TA3XZ3GCSPPJWUZQGDDI7ZCWPX","short_pith_number":"pith:TA3XZ3GC","canonical_record":{"source":{"id":"1902.08708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-23T00:13:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96114f83ff82599a2b4b0aaf363e4086f4af6d54410c463c60770fdafe67061f","abstract_canon_sha256":"599bd5b68dfb0a2ea99d9afb45ba309f58b2312c44a67b491e61db08c79b17b8"},"schema_version":"1.0"},"canonical_sha256":"98377cecc293de9b533030c68fe4567ddb4a659d730313c9753f35447256a421","source":{"kind":"arxiv","id":"1902.08708","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08708","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08708v2","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08708","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"TA3XZ3GCSPPJ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TA3XZ3GCSPPJWUZQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TA3XZ3GC","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TA3XZ3GCSPPJWUZQGDDI7ZCWPX","target":"record","payload":{"canonical_record":{"source":{"id":"1902.08708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-23T00:13:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96114f83ff82599a2b4b0aaf363e4086f4af6d54410c463c60770fdafe67061f","abstract_canon_sha256":"599bd5b68dfb0a2ea99d9afb45ba309f58b2312c44a67b491e61db08c79b17b8"},"schema_version":"1.0"},"canonical_sha256":"98377cecc293de9b533030c68fe4567ddb4a659d730313c9753f35447256a421","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.181251Z","signature_b64":"OPFhHeUSP/f5p3jmRUHJrnThtOzTfibSyctCPU6lXfv5ylFqbe8Ty4Q1s2gCpOPTuD0bsB2pNDmZgsuI1yhjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98377cecc293de9b533030c68fe4567ddb4a659d730313c9753f35447256a421","last_reissued_at":"2026-05-17T23:43:23.180675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.180675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.08708","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74uTUfJcXCzV9LxELZxnv7cS82PtHPWGN5tzew6U8RXkuailSFLlqfeO3PL4zlxb/1W1y8Hp3uf612HVj1ZZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:19:34.561886Z"},"content_sha256":"c365d8cf8adea3d31ceb33955a266c5ecb8498f637e2c98f92b30984337139ad","schema_version":"1.0","event_id":"sha256:c365d8cf8adea3d31ceb33955a266c5ecb8498f637e2c98f92b30984337139ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TA3XZ3GCSPPJWUZQGDDI7ZCWPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elena Smirnova, Elvis Dohmatob, J\\'er\\'emie Mary","submitted_at":"2019-02-23T00:13:42Z","abstract_excerpt":"Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in high-dimensional state/action space due to increased number of low-performing actions. In this work, we consider risk-averse exploration in approximate RL setting. To ensure safety during learning, we propose the distributionally robust policy iteration scheme that provides lower bound guarantee on state-values. Our approach induces a dynamic level of risk to preve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08708","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vm4oBNQn2BU1DiGpfTHHAc/ONYSoZ6EgdsV2caWH2Tf0qom12/sGCSw4RqyFO+7W4h0Y5EHOgZ7dJLrfqRj2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:19:34.562626Z"},"content_sha256":"3dbcc17ed7aa5a11824ce9af421fe3827e82b8404b721669fa10cc0f15a7fb01","schema_version":"1.0","event_id":"sha256:3dbcc17ed7aa5a11824ce9af421fe3827e82b8404b721669fa10cc0f15a7fb01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/bundle.json","state_url":"https://pith.science/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T13:19:34Z","links":{"resolver":"https://pith.science/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX","bundle":"https://pith.science/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/bundle.json","state":"https://pith.science/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TA3XZ3GCSPPJWUZQGDDI7ZCWPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TA3XZ3GCSPPJWUZQGDDI7ZCWPX","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":"599bd5b68dfb0a2ea99d9afb45ba309f58b2312c44a67b491e61db08c79b17b8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-23T00:13:42Z","title_canon_sha256":"96114f83ff82599a2b4b0aaf363e4086f4af6d54410c463c60770fdafe67061f"},"schema_version":"1.0","source":{"id":"1902.08708","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.08708","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"1902.08708v2","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08708","created_at":"2026-05-17T23:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"TA3XZ3GCSPPJ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TA3XZ3GCSPPJWUZQ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TA3XZ3GC","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:3dbcc17ed7aa5a11824ce9af421fe3827e82b8404b721669fa10cc0f15a7fb01","target":"graph","created_at":"2026-05-17T23:43:23Z","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"},"paper":{"abstract_excerpt":"Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in high-dimensional state/action space due to increased number of low-performing actions. In this work, we consider risk-averse exploration in approximate RL setting. To ensure safety during learning, we propose the distributionally robust policy iteration scheme that provides lower bound guarantee on state-values. Our approach induces a dynamic level of risk to preve","authors_text":"Elena Smirnova, Elvis Dohmatob, J\\'er\\'emie Mary","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-23T00:13:42Z","title":"Distributionally Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08708","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:c365d8cf8adea3d31ceb33955a266c5ecb8498f637e2c98f92b30984337139ad","target":"record","created_at":"2026-05-17T23:43:23Z","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":"599bd5b68dfb0a2ea99d9afb45ba309f58b2312c44a67b491e61db08c79b17b8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-23T00:13:42Z","title_canon_sha256":"96114f83ff82599a2b4b0aaf363e4086f4af6d54410c463c60770fdafe67061f"},"schema_version":"1.0","source":{"id":"1902.08708","kind":"arxiv","version":2}},"canonical_sha256":"98377cecc293de9b533030c68fe4567ddb4a659d730313c9753f35447256a421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98377cecc293de9b533030c68fe4567ddb4a659d730313c9753f35447256a421","first_computed_at":"2026-05-17T23:43:23.180675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:23.180675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPFhHeUSP/f5p3jmRUHJrnThtOzTfibSyctCPU6lXfv5ylFqbe8Ty4Q1s2gCpOPTuD0bsB2pNDmZgsuI1yhjDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:23.181251Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.08708","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c365d8cf8adea3d31ceb33955a266c5ecb8498f637e2c98f92b30984337139ad","sha256:3dbcc17ed7aa5a11824ce9af421fe3827e82b8404b721669fa10cc0f15a7fb01"],"state_sha256":"267005e759bbccbb0cee4600ec58e0acba06b3ff4f7777dbc5643c48e8716a34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uAE8kRU7J5UumormJQg2RFQDKANOwFmIRYL9v+YJMZG2CfSAcQs7V3VLKiOPNx8BODnnuSoGCGE0J7TjOwhRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T13:19:34.566545Z","bundle_sha256":"5d4fb06d11f8dd157cb5333cc24ed50729c694d915be078183e452092f1e8d5a"}}