{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RSQWU4VDZFG665RKPCIYRPGLEJ","short_pith_number":"pith:RSQWU4VD","canonical_record":{"source":{"id":"2106.02249","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:28:46Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"9d57b8deb7465ffc65a329de1efbaebe63a24598592937fd6d19cb1b3b399d5e","abstract_canon_sha256":"19d6e027def23b3d4c9b4b95033817bd4c989f0960b8feafc56b5b5988d633b1"},"schema_version":"1.0"},"canonical_sha256":"8ca16a72a3c94def762a789188bccb226cfbe6454dfd5fd88ad9e2a300d985de","source":{"kind":"arxiv","id":"2106.02249","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02249","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02249v5","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02249","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"RSQWU4VDZFG6","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"RSQWU4VDZFG665RK","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"RSQWU4VD","created_at":"2026-07-05T04:03:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RSQWU4VDZFG665RKPCIYRPGLEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02249","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:28:46Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"9d57b8deb7465ffc65a329de1efbaebe63a24598592937fd6d19cb1b3b399d5e","abstract_canon_sha256":"19d6e027def23b3d4c9b4b95033817bd4c989f0960b8feafc56b5b5988d633b1"},"schema_version":"1.0"},"canonical_sha256":"8ca16a72a3c94def762a789188bccb226cfbe6454dfd5fd88ad9e2a300d985de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:11.727510Z","signature_b64":"JWbTe5TN+tgO4nrG+ljfIFNhwVc3qVJg8xzgLPITFocK40/nyECK6zkCVF/vJ62qiURhQGyuBgVpfS9Y0D3DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ca16a72a3c94def762a789188bccb226cfbe6454dfd5fd88ad9e2a300d985de","last_reissued_at":"2026-07-05T04:03:11.727060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:11.727060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02249","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5I005JfYuvQkiWrgaOXP4/W412WO5yeoT0TNz6NRgR0ST+VzawRK9G1W0j15zuwM4EyRCbp/N+hNHgPycP+pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:05:59.552077Z"},"content_sha256":"91fe1f4061b441ff52778ed1136b39cf6d86a1029e9466a580563df0f0d6920e","schema_version":"1.0","event_id":"sha256:91fe1f4061b441ff52778ed1136b39cf6d86a1029e9466a580563df0f0d6920e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RSQWU4VDZFG665RKPCIYRPGLEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robustifying Reinforcement Learning Policies with $\\mathcal{L}_1$ Adaptive Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Bo Li, Evangelos Theodorou, Manan Gandhi, Naira Hovakimyan, Pan Zhao, Yikun Cheng","submitted_at":"2021-06-04T04:28:46Z","abstract_excerpt":"A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic variation scenarios through robust or adversarial training. These methods could lead to conservative performance due to emphasis on the worst case, and often involve tedious modifications to the training environment. We propose an approach to robustifying a pre-trained non-robust RL policy with $\\mathcal{L}_1$ adaptive control. Leveraging the capability of an $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02249","kind":"arxiv","version":5},"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/2106.02249/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":"2026-07-05T04:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHB1AMMkxhiOo2navCiugmtSifT9BNN0RrnHZeibq1B6rzmHKcZ03NOKqYiEaC6gmZlUUcmgfdC7l/GVd+5HBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:05:59.552466Z"},"content_sha256":"61c0be32d6ad3aec78b232bc6192eb88cc4fa3b151f199ad411082af5c97a638","schema_version":"1.0","event_id":"sha256:61c0be32d6ad3aec78b232bc6192eb88cc4fa3b151f199ad411082af5c97a638"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/bundle.json","state_url":"https://pith.science/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/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":"2026-07-07T13:05:59Z","links":{"resolver":"https://pith.science/pith/RSQWU4VDZFG665RKPCIYRPGLEJ","bundle":"https://pith.science/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/bundle.json","state":"https://pith.science/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSQWU4VDZFG665RKPCIYRPGLEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RSQWU4VDZFG665RKPCIYRPGLEJ","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":"19d6e027def23b3d4c9b4b95033817bd4c989f0960b8feafc56b5b5988d633b1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:28:46Z","title_canon_sha256":"9d57b8deb7465ffc65a329de1efbaebe63a24598592937fd6d19cb1b3b399d5e"},"schema_version":"1.0","source":{"id":"2106.02249","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02249","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02249v5","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02249","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"RSQWU4VDZFG6","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"RSQWU4VDZFG665RK","created_at":"2026-07-05T04:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"RSQWU4VD","created_at":"2026-07-05T04:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:61c0be32d6ad3aec78b232bc6192eb88cc4fa3b151f199ad411082af5c97a638","target":"graph","created_at":"2026-07-05T04:03:11Z","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/2106.02249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic variation scenarios through robust or adversarial training. These methods could lead to conservative performance due to emphasis on the worst case, and often involve tedious modifications to the training environment. We propose an approach to robustifying a pre-trained non-robust RL policy with $\\mathcal{L}_1$ adaptive control. Leveraging the capability of an $\\","authors_text":"Bo Li, Evangelos Theodorou, Manan Gandhi, Naira Hovakimyan, Pan Zhao, Yikun Cheng","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:28:46Z","title":"Robustifying Reinforcement Learning Policies with $\\mathcal{L}_1$ Adaptive Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02249","kind":"arxiv","version":5},"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":"sha256:91fe1f4061b441ff52778ed1136b39cf6d86a1029e9466a580563df0f0d6920e","target":"record","created_at":"2026-07-05T04:03:11Z","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":"19d6e027def23b3d4c9b4b95033817bd4c989f0960b8feafc56b5b5988d633b1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:28:46Z","title_canon_sha256":"9d57b8deb7465ffc65a329de1efbaebe63a24598592937fd6d19cb1b3b399d5e"},"schema_version":"1.0","source":{"id":"2106.02249","kind":"arxiv","version":5}},"canonical_sha256":"8ca16a72a3c94def762a789188bccb226cfbe6454dfd5fd88ad9e2a300d985de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ca16a72a3c94def762a789188bccb226cfbe6454dfd5fd88ad9e2a300d985de","first_computed_at":"2026-07-05T04:03:11.727060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:11.727060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JWbTe5TN+tgO4nrG+ljfIFNhwVc3qVJg8xzgLPITFocK40/nyECK6zkCVF/vJ62qiURhQGyuBgVpfS9Y0D3DDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:11.727510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02249","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91fe1f4061b441ff52778ed1136b39cf6d86a1029e9466a580563df0f0d6920e","sha256:61c0be32d6ad3aec78b232bc6192eb88cc4fa3b151f199ad411082af5c97a638"],"state_sha256":"070e3b3a93b5a602f644ad08ff6c460bb4a55c1d793f6fb53e9b5a037d6a3e82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpvktMPqaUazMNy8GeMXgQ6lrlC3t/6t0bOt45xGWbSAmLUj4zZj2jtu3fvWpicVdKeAGWPUkRU5IiPTURFEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:05:59.554919Z","bundle_sha256":"8ba439e5e3622df3f62091727339e862f658f274298cfa970071e16175648ecb"}}