{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RGTCZ7C2QYYACAPPDZ7BKZ6SHR","short_pith_number":"pith:RGTCZ7C2","canonical_record":{"source":{"id":"2006.00945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T13:48:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"01c9901d2b6853b5e7cbbd46bb5d0c9c0d271bdfbafbbd89df4bf4aacbe44e99","abstract_canon_sha256":"5a93c4a6cb93d56b19708feb0e6f969e234d450be0e661353f55d1579f53f3c0"},"schema_version":"1.0"},"canonical_sha256":"89a62cfc5a86300101ef1e7e1567d23c6f587a12a834b989663b776b2ecd3230","source":{"kind":"arxiv","id":"2006.00945","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00945","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00945v1","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00945","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"RGTCZ7C2QYYA","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"RGTCZ7C2QYYACAPP","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"RGTCZ7C2","created_at":"2026-07-05T01:07:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RGTCZ7C2QYYACAPPDZ7BKZ6SHR","target":"record","payload":{"canonical_record":{"source":{"id":"2006.00945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T13:48:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"01c9901d2b6853b5e7cbbd46bb5d0c9c0d271bdfbafbbd89df4bf4aacbe44e99","abstract_canon_sha256":"5a93c4a6cb93d56b19708feb0e6f969e234d450be0e661353f55d1579f53f3c0"},"schema_version":"1.0"},"canonical_sha256":"89a62cfc5a86300101ef1e7e1567d23c6f587a12a834b989663b776b2ecd3230","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:06.947913Z","signature_b64":"hbRs/x4LMlSXHbNUipeoRhTUIO9S2N3owinMNOlJwtEICBA7g9Ld/Pprg4milX83ZcVEcZMYBqIP6a/8OLAABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a62cfc5a86300101ef1e7e1567d23c6f587a12a834b989663b776b2ecd3230","last_reissued_at":"2026-07-05T01:07:06.947370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:06.947370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.00945","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":"2026-07-05T01:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGRRybtkbWoDnFgnkGcIdpaMxuPoH0SZIAv/eNIyip4tNafyVlg+kXDTbEjUHJrQhxrX8igr3a+CudLBSmOyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:05:08.183603Z"},"content_sha256":"72d0a57d5b7f426014397e8a96b768277dc2e8f62792e197b793636d9e5abaa8","schema_version":"1.0","event_id":"sha256:72d0a57d5b7f426014397e8a96b768277dc2e8f62792e197b793636d9e5abaa8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RGTCZ7C2QYYACAPPDZ7BKZ6SHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning with Wasserstein Constraint","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawei Yin, Liang Pang, Linfang Hou, Xin Hong, Yanyan Lan, Zhiming Ma","submitted_at":"2020-06-01T13:48:59Z","abstract_excerpt":"Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness through disturbing the current state or simulating environmental parameters in a heuristic way, which lack quantified robustness to the system dynamics (i.e. transition probability). To overcome this issue, we leverage Wasserstein distance to measure the disturbance to the reference transition kernel. With Wasserstein distance, we are able to connect transition kernel disturbance to the state disturbance, i.e. reduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00945","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/2006.00945/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":"2026-07-05T01:07:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzGO4nxdcoCpvkpJ5+jYjnVhhKKhixjrDtYX60sUCKWKhRUc3b0in2JWFfYxKmLC6JObcW8YWmG7s8rzm70nBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:05:08.184042Z"},"content_sha256":"c746c3d0931d25dd907b8594d67d5327e9348b83f2dd3b3bde56e98c0df01e65","schema_version":"1.0","event_id":"sha256:c746c3d0931d25dd907b8594d67d5327e9348b83f2dd3b3bde56e98c0df01e65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/bundle.json","state_url":"https://pith.science/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/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":"2026-07-19T10:05:08Z","links":{"resolver":"https://pith.science/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR","bundle":"https://pith.science/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/bundle.json","state":"https://pith.science/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGTCZ7C2QYYACAPPDZ7BKZ6SHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RGTCZ7C2QYYACAPPDZ7BKZ6SHR","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":"5a93c4a6cb93d56b19708feb0e6f969e234d450be0e661353f55d1579f53f3c0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T13:48:59Z","title_canon_sha256":"01c9901d2b6853b5e7cbbd46bb5d0c9c0d271bdfbafbbd89df4bf4aacbe44e99"},"schema_version":"1.0","source":{"id":"2006.00945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.00945","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2006.00945v1","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00945","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"RGTCZ7C2QYYA","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"RGTCZ7C2QYYACAPP","created_at":"2026-07-05T01:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"RGTCZ7C2","created_at":"2026-07-05T01:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:c746c3d0931d25dd907b8594d67d5327e9348b83f2dd3b3bde56e98c0df01e65","target":"graph","created_at":"2026-07-05T01:07:06Z","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/2006.00945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics. Existing learning algorithms usually enable the robustness through disturbing the current state or simulating environmental parameters in a heuristic way, which lack quantified robustness to the system dynamics (i.e. transition probability). To overcome this issue, we leverage Wasserstein distance to measure the disturbance to the reference transition kernel. With Wasserstein distance, we are able to connect transition kernel disturbance to the state disturbance, i.e. reduce ","authors_text":"Dawei Yin, Liang Pang, Linfang Hou, Xin Hong, Yanyan Lan, Zhiming Ma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T13:48:59Z","title":"Robust Reinforcement Learning with Wasserstein Constraint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00945","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":"sha256:72d0a57d5b7f426014397e8a96b768277dc2e8f62792e197b793636d9e5abaa8","target":"record","created_at":"2026-07-05T01:07:06Z","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":"5a93c4a6cb93d56b19708feb0e6f969e234d450be0e661353f55d1579f53f3c0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T13:48:59Z","title_canon_sha256":"01c9901d2b6853b5e7cbbd46bb5d0c9c0d271bdfbafbbd89df4bf4aacbe44e99"},"schema_version":"1.0","source":{"id":"2006.00945","kind":"arxiv","version":1}},"canonical_sha256":"89a62cfc5a86300101ef1e7e1567d23c6f587a12a834b989663b776b2ecd3230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89a62cfc5a86300101ef1e7e1567d23c6f587a12a834b989663b776b2ecd3230","first_computed_at":"2026-07-05T01:07:06.947370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:06.947370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hbRs/x4LMlSXHbNUipeoRhTUIO9S2N3owinMNOlJwtEICBA7g9Ld/Pprg4milX83ZcVEcZMYBqIP6a/8OLAABA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:06.947913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.00945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d0a57d5b7f426014397e8a96b768277dc2e8f62792e197b793636d9e5abaa8","sha256:c746c3d0931d25dd907b8594d67d5327e9348b83f2dd3b3bde56e98c0df01e65"],"state_sha256":"84a59bdcf860e5fd6d826e99319bcb065e704154fa6fd738213b6e00629b34d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3sF9FA2Px6GOu9D5kyPsIkwBTErefmj8GmJHE1WPhKcmZfcHCtUlEyhhEFHTUutZHAmDQX2V8SEb/DMXN2pCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T10:05:08.186158Z","bundle_sha256":"f659bbb6d55f03fc43ca123d295296e26e0c5495f9153c7dbcf20bd8c793ebfe"}}