{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AALOQM6Z2KYU63PLKTWJ3I7BWJ","short_pith_number":"pith:AALOQM6Z","canonical_record":{"source":{"id":"2010.04870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T01:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"8eb359fd52d11f6ec751e78bbed6e2c7ad8466f145a27b596c51d1c11c4c71ad","abstract_canon_sha256":"78748146145eeb976e97e115e443d4bbf3b280aa7647a0fef671f0587e11e3dc"},"schema_version":"1.0"},"canonical_sha256":"0016e833d9d2b14f6deb54ec9da3e1b27a1cf18ce6c0b2ef45f6e111ef8f9261","source":{"kind":"arxiv","id":"2010.04870","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04870","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04870v1","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04870","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"AALOQM6Z2KYU","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"AALOQM6Z2KYU63PL","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"AALOQM6Z","created_at":"2026-07-05T01:42:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AALOQM6Z2KYU63PLKTWJ3I7BWJ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.04870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T01:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"8eb359fd52d11f6ec751e78bbed6e2c7ad8466f145a27b596c51d1c11c4c71ad","abstract_canon_sha256":"78748146145eeb976e97e115e443d4bbf3b280aa7647a0fef671f0587e11e3dc"},"schema_version":"1.0"},"canonical_sha256":"0016e833d9d2b14f6deb54ec9da3e1b27a1cf18ce6c0b2ef45f6e111ef8f9261","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:00.173765Z","signature_b64":"8nBjRELkkVSZDTGiAEb/Q7ka1KrZbvMtBY4xO5DuyW2NCr2XVcoxTGNK1eneuDOnoq3HZFiRjzTcVbrno6XwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0016e833d9d2b14f6deb54ec9da3e1b27a1cf18ce6c0b2ef45f6e111ef8f9261","last_reissued_at":"2026-07-05T01:42:00.173365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:00.173365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.04870","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":"2026-07-05T01:42:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EFLfTbjGQYP16kV6CbnFi4Q1FbD+LPIGyxtB0VjYhcPCR8vNQjk7f5Z1MQpdBwoeY2Zb2TohROQuWYkVKy7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:34:27.809244Z"},"content_sha256":"e31613ccd2babcaf173148ce4f9acc41c51e662075cbf10e0b7dedf9164d19b0","schema_version":"1.0","event_id":"sha256:e31613ccd2babcaf173148ce4f9acc41c51e662075cbf10e0b7dedf9164d19b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AALOQM6Z2KYU63PLKTWJ3I7BWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jeroen van Baar, Mouhacine Benosman, Reazul Hasan Russel","submitted_at":"2020-10-10T01:53:37Z","abstract_excerpt":"In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision process (CMDP), with the theory of robust Markov decision process (RMDP), leading to a formulation of robust constrained-MDPs (RCMDP). This formulation, simple in essence, allows us to design RL algorithms that are robust in performance, and provides constraint satisfaction guarantees, with respect to uncertainties in the system's states transition probabilitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04870","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/2010.04870/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":"2026-07-05T01:42:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2gvWGRw6t/dmeU7zbN3S+WbCVQa11PPeLPApG8j7CUf/9f8QOcWu0ce2+YYPpAe4kPt2lYv82vTHHtWM+PtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:34:27.809731Z"},"content_sha256":"4af899aff7e24b67b260827d89b2aef8c25d35b3ea3f0a558e60cf1eed46bc97","schema_version":"1.0","event_id":"sha256:4af899aff7e24b67b260827d89b2aef8c25d35b3ea3f0a558e60cf1eed46bc97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/bundle.json","state_url":"https://pith.science/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/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":"2026-08-05T16:34:27Z","links":{"resolver":"https://pith.science/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ","bundle":"https://pith.science/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/bundle.json","state":"https://pith.science/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AALOQM6Z2KYU63PLKTWJ3I7BWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AALOQM6Z2KYU63PLKTWJ3I7BWJ","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":"78748146145eeb976e97e115e443d4bbf3b280aa7647a0fef671f0587e11e3dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T01:53:37Z","title_canon_sha256":"8eb359fd52d11f6ec751e78bbed6e2c7ad8466f145a27b596c51d1c11c4c71ad"},"schema_version":"1.0","source":{"id":"2010.04870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04870","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04870v1","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04870","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"AALOQM6Z2KYU","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"AALOQM6Z2KYU63PL","created_at":"2026-07-05T01:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"AALOQM6Z","created_at":"2026-07-05T01:42:00Z"}],"graph_snapshots":[{"event_id":"sha256:4af899aff7e24b67b260827d89b2aef8c25d35b3ea3f0a558e60cf1eed46bc97","target":"graph","created_at":"2026-07-05T01:42:00Z","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/2010.04870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties. Indeed, in the framework of model-based RL, we propose to merge the theory of constrained Markov decision process (CMDP), with the theory of robust Markov decision process (RMDP), leading to a formulation of robust constrained-MDPs (RCMDP). This formulation, simple in essence, allows us to design RL algorithms that are robust in performance, and provides constraint satisfaction guarantees, with respect to uncertainties in the system's states transition probabilitie","authors_text":"Jeroen van Baar, Mouhacine Benosman, Reazul Hasan Russel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T01:53:37Z","title":"Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04870","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:e31613ccd2babcaf173148ce4f9acc41c51e662075cbf10e0b7dedf9164d19b0","target":"record","created_at":"2026-07-05T01:42:00Z","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":"78748146145eeb976e97e115e443d4bbf3b280aa7647a0fef671f0587e11e3dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-10T01:53:37Z","title_canon_sha256":"8eb359fd52d11f6ec751e78bbed6e2c7ad8466f145a27b596c51d1c11c4c71ad"},"schema_version":"1.0","source":{"id":"2010.04870","kind":"arxiv","version":1}},"canonical_sha256":"0016e833d9d2b14f6deb54ec9da3e1b27a1cf18ce6c0b2ef45f6e111ef8f9261","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0016e833d9d2b14f6deb54ec9da3e1b27a1cf18ce6c0b2ef45f6e111ef8f9261","first_computed_at":"2026-07-05T01:42:00.173365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:00.173365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nBjRELkkVSZDTGiAEb/Q7ka1KrZbvMtBY4xO5DuyW2NCr2XVcoxTGNK1eneuDOnoq3HZFiRjzTcVbrno6XwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:00.173765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e31613ccd2babcaf173148ce4f9acc41c51e662075cbf10e0b7dedf9164d19b0","sha256:4af899aff7e24b67b260827d89b2aef8c25d35b3ea3f0a558e60cf1eed46bc97"],"state_sha256":"c8fe1d1305a4da9b9b44a3d9b9fd40cea9a5b0c95cdeb99747aaaaf14b6aca12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j4wGj9zRkz0hkaZRK+TPKBYCoW5WzuSwhzhabt6qe7HN0X4EFzgjFc/s99OnBRtnnvm6kG67tuNI+1g4F4I7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:34:27.813724Z","bundle_sha256":"343150276eff2485a2fcae2cd82116e659ad8db0576d9e1070cbef397c3431d9"}}