{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FIJ7BXNS7AMLWAEI7WIU3AHJ76","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":"8c979e34d49f837521d80563cecb5b1b5f16a15b9484e2208ebec06dea2b55e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T07:54:15Z","title_canon_sha256":"27217468c22673bda0ef9b77269bc8fec491a39767c238827ffc06d2d112461d"},"schema_version":"1.0","source":{"id":"2205.11104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11104","created_at":"2026-07-05T04:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11104v1","created_at":"2026-07-05T04:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11104","created_at":"2026-07-05T04:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"FIJ7BXNS7AML","created_at":"2026-07-05T04:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"FIJ7BXNS7AMLWAEI","created_at":"2026-07-05T04:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"FIJ7BXNS","created_at":"2026-07-05T04:25:27Z"}],"graph_snapshots":[{"event_id":"sha256:5e24f8c031b824643fbd1dbdc4a4de5fbdb5768ca0077ebfc301a488e3b5fe88","target":"graph","created_at":"2026-07-05T04:25:27Z","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/2205.11104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"At first sight it may seem straightforward to use recurrent layers in Deep Reinforcement Learning algorithms to enable agents to make use of memory in the setting of partially observable environments. Starting from widely used Proximal Policy Optimization (PPO), we highlight vital details that one must get right when adding recurrence to achieve a correct and efficient implementation, namely: properly shaping the neural net's forward pass, arranging the training data, correspondingly selecting hidden states for sequence beginnings and masking paddings for loss computation. We further explore t","authors_text":"Frank Zimmer, Marco Pleines, Matthias Pallasch, Mike Preuss","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T07:54:15Z","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11104","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:b037346650910133c7260bfa8e0bfe23dd8a7c1ae7c73a6e6ea81c9cef89f7f0","target":"record","created_at":"2026-07-05T04:25:27Z","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":"8c979e34d49f837521d80563cecb5b1b5f16a15b9484e2208ebec06dea2b55e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T07:54:15Z","title_canon_sha256":"27217468c22673bda0ef9b77269bc8fec491a39767c238827ffc06d2d112461d"},"schema_version":"1.0","source":{"id":"2205.11104","kind":"arxiv","version":1}},"canonical_sha256":"2a13f0ddb2f818bb0088fd914d80e9ff890509f3abebd7d8df4b6ecfd60d0ace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a13f0ddb2f818bb0088fd914d80e9ff890509f3abebd7d8df4b6ecfd60d0ace","first_computed_at":"2026-07-05T04:25:27.347650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:27.347650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xOcM4H1CJk3hV1CwOpZc0DNqfbjBBUYEB1g+MvLBOzyLeybIrQBURp1OUjVfMSavPDWr1vZmKJcWlmQMdruvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:27.348411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b037346650910133c7260bfa8e0bfe23dd8a7c1ae7c73a6e6ea81c9cef89f7f0","sha256:5e24f8c031b824643fbd1dbdc4a4de5fbdb5768ca0077ebfc301a488e3b5fe88"],"state_sha256":"22037196f9f281961b750dde587a62776b5d17ccc129f25b436774ab9c6d4e12"}