{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WF2A5IIAEQXI2ITKVP5LSD7EUH","short_pith_number":"pith:WF2A5IIA","canonical_record":{"source":{"id":"1802.03236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T12:52:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"72a04995b5afbf287b7df8e8d47b0495ac18d71b035e69e3246c0890fea14dba","abstract_canon_sha256":"df8d876209549a65ad69de840f4a5f6d1a65b85a13874511c1c424a7663e6f3d"},"schema_version":"1.0"},"canonical_sha256":"b1740ea100242e8d226aabfab90fe4a1f397704105d11d71f665bbfeea2c5dc0","source":{"kind":"arxiv","id":"1802.03236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03236","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03236v1","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03236","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"WF2A5IIAEQXI","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WF2A5IIAEQXI2ITK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WF2A5IIA","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WF2A5IIAEQXI2ITKVP5LSD7EUH","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T12:52:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"72a04995b5afbf287b7df8e8d47b0495ac18d71b035e69e3246c0890fea14dba","abstract_canon_sha256":"df8d876209549a65ad69de840f4a5f6d1a65b85a13874511c1c424a7663e6f3d"},"schema_version":"1.0"},"canonical_sha256":"b1740ea100242e8d226aabfab90fe4a1f397704105d11d71f665bbfeea2c5dc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:58.207526Z","signature_b64":"35IStrsZk96X305+9qYRn0B/05unAoIPCbRZ3HeponM0vI53Fl9h1vJTFhwO3P89vl5woofAC7/qAK9QGsR8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1740ea100242e8d226aabfab90fe4a1f397704105d11d71f665bbfeea2c5dc0","last_reissued_at":"2026-05-18T00:23:58.206933Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:58.206933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03236","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":"2026-05-18T00:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEuwhb5ZDZqdaQB3D2ZDtx/WVTNTertAc/0rJlxGADXbh9/t9n2yNr1OWuXeDw14tkGxij3QtOsgf4GPATdUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:35:43.232376Z"},"content_sha256":"b3fc6b5eefc39f418b0e9a3f57d1c6376bdd2702a9412b08e0343e2fd9399b03","schema_version":"1.0","event_id":"sha256:b3fc6b5eefc39f418b0e9a3f57d1c6376bdd2702a9412b08e0343e2fd9399b03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WF2A5IIAEQXI2ITKVP5LSD7EUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Daniel J. Mankowitz, Doina Precup, Pierre-Luc Bacon, Shie Mannor, Timothy A. Mann","submitted_at":"2018-02-09T12:52:06Z","abstract_excerpt":"Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally abstract actions, in the framework of options. We present a Robust Options Policy Iteration (ROPI) algorithm with convergence guarantees, which learns options that are robust to model uncertainty. We utilize ROPI to learn robust options with the Robust Options Deep Q Network (RO-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03236","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":""},"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":"2026-05-18T00:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIZVJ7xr74N11qNxac2UNsq3VGaqxnFewJD8PeEfSdxiIFR717HJu1C/A9yTFJNyYWLJlAyOX473/qhq9OvGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:35:43.232776Z"},"content_sha256":"9342cb6c94b43f1dfd4882ad8d88345e877c9dc0e8cea687cd07e0560e870690","schema_version":"1.0","event_id":"sha256:9342cb6c94b43f1dfd4882ad8d88345e877c9dc0e8cea687cd07e0560e870690"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/bundle.json","state_url":"https://pith.science/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/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":"2026-05-20T22:35:43Z","links":{"resolver":"https://pith.science/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH","bundle":"https://pith.science/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/bundle.json","state":"https://pith.science/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WF2A5IIAEQXI2ITKVP5LSD7EUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WF2A5IIAEQXI2ITKVP5LSD7EUH","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":"df8d876209549a65ad69de840f4a5f6d1a65b85a13874511c1c424a7663e6f3d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T12:52:06Z","title_canon_sha256":"72a04995b5afbf287b7df8e8d47b0495ac18d71b035e69e3246c0890fea14dba"},"schema_version":"1.0","source":{"id":"1802.03236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03236","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03236v1","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03236","created_at":"2026-05-18T00:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"WF2A5IIAEQXI","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WF2A5IIAEQXI2ITK","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WF2A5IIA","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:9342cb6c94b43f1dfd4882ad8d88345e877c9dc0e8cea687cd07e0560e870690","target":"graph","created_at":"2026-05-18T00:23:58Z","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"},"paper":{"abstract_excerpt":"Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally abstract actions, in the framework of options. We present a Robust Options Policy Iteration (ROPI) algorithm with convergence guarantees, which learns options that are robust to model uncertainty. We utilize ROPI to learn robust options with the Robust Options Deep Q Network (RO-","authors_text":"Daniel J. Mankowitz, Doina Precup, Pierre-Luc Bacon, Shie Mannor, Timothy A. Mann","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T12:52:06Z","title":"Learning Robust Options"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03236","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:b3fc6b5eefc39f418b0e9a3f57d1c6376bdd2702a9412b08e0343e2fd9399b03","target":"record","created_at":"2026-05-18T00:23:58Z","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":"df8d876209549a65ad69de840f4a5f6d1a65b85a13874511c1c424a7663e6f3d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-09T12:52:06Z","title_canon_sha256":"72a04995b5afbf287b7df8e8d47b0495ac18d71b035e69e3246c0890fea14dba"},"schema_version":"1.0","source":{"id":"1802.03236","kind":"arxiv","version":1}},"canonical_sha256":"b1740ea100242e8d226aabfab90fe4a1f397704105d11d71f665bbfeea2c5dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1740ea100242e8d226aabfab90fe4a1f397704105d11d71f665bbfeea2c5dc0","first_computed_at":"2026-05-18T00:23:58.206933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:58.206933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35IStrsZk96X305+9qYRn0B/05unAoIPCbRZ3HeponM0vI53Fl9h1vJTFhwO3P89vl5woofAC7/qAK9QGsR8BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:58.207526Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3fc6b5eefc39f418b0e9a3f57d1c6376bdd2702a9412b08e0343e2fd9399b03","sha256:9342cb6c94b43f1dfd4882ad8d88345e877c9dc0e8cea687cd07e0560e870690"],"state_sha256":"572145141b053921933f55e75c3515ba8311179ca8ca1a5f4c776544d5d93d79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zbg5S1hIf1Tg5gxGLqa5R3EWm5jg8o2uHvkCXY9v8wbzUNa64wQMVmeInl29Hj1n3Ikp3kdLQkNyl8RsSxu5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T22:35:43.235451Z","bundle_sha256":"1994045a20ca5a09e8d28132e573d9c47bf380a00d1a9cf78b5d4a84f1525c18"}}