{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KPBIPVNPJGDPJ3EVJLYA7RDRZ2","short_pith_number":"pith:KPBIPVNP","canonical_record":{"source":{"id":"1906.07516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T12:08:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"17718303cf1c8401d0a7a83392ac4707dd5976bcc446e11341045d8da21aad6f","abstract_canon_sha256":"1c6d8bde5e52a083e4ad9ab07199fab07bb18cbf2d0865b0a2e0b9a66b92e711"},"schema_version":"1.0"},"canonical_sha256":"53c287d5af4986f4ec954af00fc471cebda70c31888c3829b2512fdb526e1138","source":{"kind":"arxiv","id":"1906.07516","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07516","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07516v2","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07516","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_12","alias_value":"KPBIPVNPJGDP","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_16","alias_value":"KPBIPVNPJGDPJ3EV","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_8","alias_value":"KPBIPVNP","created_at":"2026-07-05T00:39:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KPBIPVNPJGDPJ3EVJLYA7RDRZ2","target":"record","payload":{"canonical_record":{"source":{"id":"1906.07516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T12:08:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"17718303cf1c8401d0a7a83392ac4707dd5976bcc446e11341045d8da21aad6f","abstract_canon_sha256":"1c6d8bde5e52a083e4ad9ab07199fab07bb18cbf2d0865b0a2e0b9a66b92e711"},"schema_version":"1.0"},"canonical_sha256":"53c287d5af4986f4ec954af00fc471cebda70c31888c3829b2512fdb526e1138","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:31.767986Z","signature_b64":"k9DS2qt9/qoE4R6qiey914DJWrgi5qKTL+YUHl6gfNDIo3zJCRpiQsozjiYIYVMPTkeVbcdkEzD61PmVHFK1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53c287d5af4986f4ec954af00fc471cebda70c31888c3829b2512fdb526e1138","last_reissued_at":"2026-07-05T00:39:31.767512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:31.767512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.07516","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":"2026-07-05T00:39:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kS2rgwYNeRDYilAzWk+0eqBA6wiBzhnWrnHeYKwUd7U01Yvf0PKlwAU2UG+knfH6GBiQS6XBw5S4UCZcRbqIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:27:11.128266Z"},"content_sha256":"0081e57e201c7798a77b2f5b262e123a7a083ceab931ceb7b2281bca1f6e9c8a","schema_version":"1.0","event_id":"sha256:0081e57e201c7798a77b2f5b262e123a7a083ceab931ceb7b2281bca1f6e9c8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KPBIPVNPJGDPJ3EVJLYA7RDRZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Daniel J. Mankowitz, Jackie Kay, Jost Tobias Springenberg, Martin Riedmiller, Nir Levine, Rae Jeong, Timothy Mann, Todd Hester, Yuanyuan Shi","submitted_at":"2019-06-18T12:08:42Z","abstract_excerpt":"We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm called Maximum a-posteriori Policy Optimization (MPO). We achieve this by learning a policy that optimizes for a worst case expected return objective and derive a corresponding robust entropy-regularized Bellman contraction operator. In addition, we introduce a less conservative, sof"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07516","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.07516/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":"2026-07-05T00:39:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DUklInfJS2XsCde+hpvOr/ks/KoRF9W5nR1VEhegJsC0ljqPty0KCyq9ARZC1SYmZZK4GrwCi2OiW5a5JYEnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:27:11.128660Z"},"content_sha256":"fba0f87b5ec02b5e9ef8db4179958be130defa8562f69364aeeb700f344fc540","schema_version":"1.0","event_id":"sha256:fba0f87b5ec02b5e9ef8db4179958be130defa8562f69364aeeb700f344fc540"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/bundle.json","state_url":"https://pith.science/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/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":"2026-07-07T12:27:11Z","links":{"resolver":"https://pith.science/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2","bundle":"https://pith.science/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/bundle.json","state":"https://pith.science/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPBIPVNPJGDPJ3EVJLYA7RDRZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KPBIPVNPJGDPJ3EVJLYA7RDRZ2","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":"1c6d8bde5e52a083e4ad9ab07199fab07bb18cbf2d0865b0a2e0b9a66b92e711","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T12:08:42Z","title_canon_sha256":"17718303cf1c8401d0a7a83392ac4707dd5976bcc446e11341045d8da21aad6f"},"schema_version":"1.0","source":{"id":"1906.07516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07516","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07516v2","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07516","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_12","alias_value":"KPBIPVNPJGDP","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_16","alias_value":"KPBIPVNPJGDPJ3EV","created_at":"2026-07-05T00:39:31Z"},{"alias_kind":"pith_short_8","alias_value":"KPBIPVNP","created_at":"2026-07-05T00:39:31Z"}],"graph_snapshots":[{"event_id":"sha256:fba0f87b5ec02b5e9ef8db4179958be130defa8562f69364aeeb700f344fc540","target":"graph","created_at":"2026-07-05T00:39:31Z","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/1906.07516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm called Maximum a-posteriori Policy Optimization (MPO). We achieve this by learning a policy that optimizes for a worst case expected return objective and derive a corresponding robust entropy-regularized Bellman contraction operator. In addition, we introduce a less conservative, sof","authors_text":"Abbas Abdolmaleki, Daniel J. Mankowitz, Jackie Kay, Jost Tobias Springenberg, Martin Riedmiller, Nir Levine, Rae Jeong, Timothy Mann, Todd Hester, Yuanyuan Shi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T12:08:42Z","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07516","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":"sha256:0081e57e201c7798a77b2f5b262e123a7a083ceab931ceb7b2281bca1f6e9c8a","target":"record","created_at":"2026-07-05T00:39:31Z","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":"1c6d8bde5e52a083e4ad9ab07199fab07bb18cbf2d0865b0a2e0b9a66b92e711","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T12:08:42Z","title_canon_sha256":"17718303cf1c8401d0a7a83392ac4707dd5976bcc446e11341045d8da21aad6f"},"schema_version":"1.0","source":{"id":"1906.07516","kind":"arxiv","version":2}},"canonical_sha256":"53c287d5af4986f4ec954af00fc471cebda70c31888c3829b2512fdb526e1138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c287d5af4986f4ec954af00fc471cebda70c31888c3829b2512fdb526e1138","first_computed_at":"2026-07-05T00:39:31.767512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:39:31.767512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9DS2qt9/qoE4R6qiey914DJWrgi5qKTL+YUHl6gfNDIo3zJCRpiQsozjiYIYVMPTkeVbcdkEzD61PmVHFK1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:39:31.767986Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0081e57e201c7798a77b2f5b262e123a7a083ceab931ceb7b2281bca1f6e9c8a","sha256:fba0f87b5ec02b5e9ef8db4179958be130defa8562f69364aeeb700f344fc540"],"state_sha256":"3b7fbc3e017360ce162350a77b0408bb797626dbb8c6579825bd62ba7104a4bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+jW96FbCQLwpIRHV4XLn1qi3iUQyugMUF44dOpY6C57NDwMPiU1Nq9aayxp5NtkwqhF69arbSulYeFb7Sj7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:27:11.130754Z","bundle_sha256":"a7d737b09b0118df1a833bb3369c4ba9133492edc3000f5d62391a49d45a25cb"}}