{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AT5EXM7PLB4Q4OMNWTZF6V2XWQ","short_pith_number":"pith:AT5EXM7P","schema_version":"1.0","canonical_sha256":"04fa4bb3ef58790e398db4f25f5757b43c7ccfa1b231763089ade0dbf5dedf73","source":{"kind":"arxiv","id":"2304.13616","version":2},"attestation_state":"computed","paper":{"title":"CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claudia Linnhoff-Popien, Fabian Ritz, Jonas N\\\"u{\\ss}lein, Leonard Feuchtinger, Philipp Altmann, Thomy Phan","submitted_at":"2023-04-26T15:19:02Z","abstract_excerpt":"The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for generalization apply data augmentation techniques to increase the diversity of training data. Even though this prevents overfitting to the training environment(s), it hinders policy optimization. Crafting a suitable observation, only containing crucial information, has been shown to be a challenging task itself. To improve data efficiency and generalization"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.13616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T15:19:02Z","cross_cats_sorted":[],"title_canon_sha256":"e4b856bbde3e1d002d031a0a16c339439093c2451c820affa1288f11fb15e368","abstract_canon_sha256":"bd9978f8dcd03058bb247039bf8a948b6a11ee649236f3053f19594dcbe8d14d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:08.029029Z","signature_b64":"vURK5Zdu57Gr8PfIYmi2UySk0tRjzN6PBeYfQhn9MdZ1Sy8leL+nBceCRYHO8ZBofYG+YkXn80IYlzcEJwwWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04fa4bb3ef58790e398db4f25f5757b43c7ccfa1b231763089ade0dbf5dedf73","last_reissued_at":"2026-07-05T07:20:08.028547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:08.028547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claudia Linnhoff-Popien, Fabian Ritz, Jonas N\\\"u{\\ss}lein, Leonard Feuchtinger, Philipp Altmann, Thomy Phan","submitted_at":"2023-04-26T15:19:02Z","abstract_excerpt":"The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for generalization apply data augmentation techniques to increase the diversity of training data. Even though this prevents overfitting to the training environment(s), it hinders policy optimization. Crafting a suitable observation, only containing crucial information, has been shown to be a challenging task itself. To improve data efficiency and generalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13616","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/2304.13616/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.13616","created_at":"2026-07-05T07:20:08.028605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13616v2","created_at":"2026-07-05T07:20:08.028605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13616","created_at":"2026-07-05T07:20:08.028605+00:00"},{"alias_kind":"pith_short_12","alias_value":"AT5EXM7PLB4Q","created_at":"2026-07-05T07:20:08.028605+00:00"},{"alias_kind":"pith_short_16","alias_value":"AT5EXM7PLB4Q4OMN","created_at":"2026-07-05T07:20:08.028605+00:00"},{"alias_kind":"pith_short_8","alias_value":"AT5EXM7P","created_at":"2026-07-05T07:20:08.028605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ","json":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ.json","graph_json":"https://pith.science/api/pith-number/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/graph.json","events_json":"https://pith.science/api/pith-number/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/events.json","paper":"https://pith.science/paper/AT5EXM7P"},"agent_actions":{"view_html":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ","download_json":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ.json","view_paper":"https://pith.science/paper/AT5EXM7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13616&json=true","fetch_graph":"https://pith.science/api/pith-number/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/action/storage_attestation","attest_author":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/action/author_attestation","sign_citation":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/action/citation_signature","submit_replication":"https://pith.science/pith/AT5EXM7PLB4Q4OMNWTZF6V2XWQ/action/replication_record"}},"created_at":"2026-07-05T07:20:08.028605+00:00","updated_at":"2026-07-05T07:20:08.028605+00:00"}