{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OKDMWGXAWUWGWC2OTR2RSQPI7I","short_pith_number":"pith:OKDMWGXA","canonical_record":{"source":{"id":"2005.00585","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T20:03:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2fe5c9ee3c1867419aae96d3d9742a842ee8408dce7215a9af3723ac91e3cfed","abstract_canon_sha256":"8b2c14cc7994ec1080a989164ff7a084384e467be457aad9a5d8b0e6dd796815"},"schema_version":"1.0"},"canonical_sha256":"7286cb1ae0b52c6b0b4e9c751941e8fa054c9216a9c596958b16d8d8d1aab1bb","source":{"kind":"arxiv","id":"2005.00585","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00585","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00585v1","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00585","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"OKDMWGXAWUWG","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"OKDMWGXAWUWGWC2O","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"OKDMWGXA","created_at":"2026-07-05T00:59:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OKDMWGXAWUWGWC2OTR2RSQPI7I","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00585","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T20:03:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2fe5c9ee3c1867419aae96d3d9742a842ee8408dce7215a9af3723ac91e3cfed","abstract_canon_sha256":"8b2c14cc7994ec1080a989164ff7a084384e467be457aad9a5d8b0e6dd796815"},"schema_version":"1.0"},"canonical_sha256":"7286cb1ae0b52c6b0b4e9c751941e8fa054c9216a9c596958b16d8d8d1aab1bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:44.107955Z","signature_b64":"BFOgHq8WNNc9RBerUZ2CVaaUIiKMwli1Yr5FaqnRSoZvrUdtzPX/Uk2pUZF/y+i1NyiOa+D0Iy/+59iglXkCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7286cb1ae0b52c6b0b4e9c751941e8fa054c9216a9c596958b16d8d8d1aab1bb","last_reissued_at":"2026-07-05T00:59:44.107484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:44.107484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00585","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6rKNL/60fKcdLWQE+VYojxp+pkdehjo7rivz7PHpAR4GLhjdsS6EQLMkr1j/sLqEtADIDnI1wMyib5JHIxEfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:02.029078Z"},"content_sha256":"05e18db9561256af62c8b9433189f8814b17fc2f8c80862d18f0fe35ca144a1d","schema_version":"1.0","event_id":"sha256:05e18db9561256af62c8b9433189f8814b17fc2f8c80862d18f0fe35ca144a1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OKDMWGXAWUWGWC2OTR2RSQPI7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Robustness via Risk Averse Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qinsheng Zhang, Rahul Singh, Yongxin Chen","submitted_at":"2020-05-01T20:03:10Z","abstract_excerpt":"One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies. Robustness is critical when the policies are trained in simulations instead of real world environment. In this work, we propose a risk-aware algorithm to learn robust policies in order to bridge the gap between simulation training and real-world implementation. Our algorithm is based on recently discovered distributional RL framework. We incorporate CVaR risk measure in sample based distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00585","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/2005.00585/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bK6mF+gRca/eppEm946BfvjbjohDx2u9FlXwzAOvje7DJMvEOPjqKR/XvxYknl11/NlC6jFKvAh0YZoRQLV/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:31:02.029463Z"},"content_sha256":"33afbb89a42f27933fd0a2b01a646ba585a1e51a0066a6a0e3bb1793889c5a70","schema_version":"1.0","event_id":"sha256:33afbb89a42f27933fd0a2b01a646ba585a1e51a0066a6a0e3bb1793889c5a70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/bundle.json","state_url":"https://pith.science/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/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":"2026-07-06T23:31:02Z","links":{"resolver":"https://pith.science/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I","bundle":"https://pith.science/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/bundle.json","state":"https://pith.science/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKDMWGXAWUWGWC2OTR2RSQPI7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OKDMWGXAWUWGWC2OTR2RSQPI7I","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":"8b2c14cc7994ec1080a989164ff7a084384e467be457aad9a5d8b0e6dd796815","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T20:03:10Z","title_canon_sha256":"2fe5c9ee3c1867419aae96d3d9742a842ee8408dce7215a9af3723ac91e3cfed"},"schema_version":"1.0","source":{"id":"2005.00585","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00585","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00585v1","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00585","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"OKDMWGXAWUWG","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"OKDMWGXAWUWGWC2O","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"OKDMWGXA","created_at":"2026-07-05T00:59:44Z"}],"graph_snapshots":[{"event_id":"sha256:33afbb89a42f27933fd0a2b01a646ba585a1e51a0066a6a0e3bb1793889c5a70","target":"graph","created_at":"2026-07-05T00:59:44Z","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/2005.00585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies. Robustness is critical when the policies are trained in simulations instead of real world environment. In this work, we propose a risk-aware algorithm to learn robust policies in order to bridge the gap between simulation training and real-world implementation. Our algorithm is based on recently discovered distributional RL framework. We incorporate CVaR risk measure in sample based distrib","authors_text":"Qinsheng Zhang, Rahul Singh, Yongxin Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T20:03:10Z","title":"Improving Robustness via Risk Averse Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00585","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":"sha256:05e18db9561256af62c8b9433189f8814b17fc2f8c80862d18f0fe35ca144a1d","target":"record","created_at":"2026-07-05T00:59:44Z","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":"8b2c14cc7994ec1080a989164ff7a084384e467be457aad9a5d8b0e6dd796815","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T20:03:10Z","title_canon_sha256":"2fe5c9ee3c1867419aae96d3d9742a842ee8408dce7215a9af3723ac91e3cfed"},"schema_version":"1.0","source":{"id":"2005.00585","kind":"arxiv","version":1}},"canonical_sha256":"7286cb1ae0b52c6b0b4e9c751941e8fa054c9216a9c596958b16d8d8d1aab1bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7286cb1ae0b52c6b0b4e9c751941e8fa054c9216a9c596958b16d8d8d1aab1bb","first_computed_at":"2026-07-05T00:59:44.107484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:44.107484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BFOgHq8WNNc9RBerUZ2CVaaUIiKMwli1Yr5FaqnRSoZvrUdtzPX/Uk2pUZF/y+i1NyiOa+D0Iy/+59iglXkCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:44.107955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00585","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e18db9561256af62c8b9433189f8814b17fc2f8c80862d18f0fe35ca144a1d","sha256:33afbb89a42f27933fd0a2b01a646ba585a1e51a0066a6a0e3bb1793889c5a70"],"state_sha256":"12ddbf85da21d684a613793a69c041310aeb14c373defb4773ecb30c11343b45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6o0Q42cc2+kmJuPhIi+WYZ8jkNoj9jOju9+QFhp1URaGXfHbJ2jQUih61AvSCQOo6U95dLPkYMfhyLE3BVgkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:31:02.031446Z","bundle_sha256":"1a03def18ef0187d0ba2e555fc99a9ae18f62e1a8dda9c1f2da4a867eded6a41"}}