{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QMZJBJRBXTFPCINHK5FV6WGDGH","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":"adc35a8ed7d36ae1b4d2939a90fef8c025659b6ef3a7c3ab7b14eaaa8dba0633","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:41:05Z","title_canon_sha256":"27a3f3ad1e94ee104184a1963c9c82d27b8049d3b8a82b6c1079922cdc3c7a7f"},"schema_version":"1.0","source":{"id":"2302.05740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05740","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05740v1","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05740","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"QMZJBJRBXTFP","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"QMZJBJRBXTFPCINH","created_at":"2026-07-05T05:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"QMZJBJRB","created_at":"2026-07-05T05:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:cc80b854bdfa330288c7ff1be2deb91e6ed6b193ff6be02b1044b6669a82242d","target":"graph","created_at":"2026-07-05T05:40:57Z","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/2302.05740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The discounting mechanism in Reinforcement Learning determines the relative importance of future and present rewards. While exponential discounting is widely used in practice, non-exponential discounting methods that align with human behavior are often desirable for creating human-like agents. However, non-exponential discounting methods cannot be directly applied in modern on-policy actor-critic algorithms. To address this issue, we propose Universal Generalized Advantage Estimation (UGAE), which allows for the computation of GAE advantage values with arbitrary discounting. Additionally, we i","authors_text":"Ariel Kwiatkowski, Julien Pettr\\'e, Marie-Paule Cani, Vicky Kalogeiton","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:41:05Z","title":"UGAE: A Novel Approach to Non-exponential Discounting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05740","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":"sha256:5ece5d66d6b4ed880a6220c55356f72a394bdf4f171b1eabc5a959156ec3abc9","target":"record","created_at":"2026-07-05T05:40:57Z","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":"adc35a8ed7d36ae1b4d2939a90fef8c025659b6ef3a7c3ab7b14eaaa8dba0633","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-11T16:41:05Z","title_canon_sha256":"27a3f3ad1e94ee104184a1963c9c82d27b8049d3b8a82b6c1079922cdc3c7a7f"},"schema_version":"1.0","source":{"id":"2302.05740","kind":"arxiv","version":1}},"canonical_sha256":"833290a621bccaf121a7574b5f58c331ffa38f6629f34ee20c2f5607c7f101d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"833290a621bccaf121a7574b5f58c331ffa38f6629f34ee20c2f5607c7f101d1","first_computed_at":"2026-07-05T05:40:57.774474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:57.774474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N1rVAX7Hn5liWt/SIXZOrQR4su7A20MBEEQ6x+pCJwz9YkQOjakwPJcCouj9cDx8fWKJBgRdnh7DGD2hFyEtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:57.774920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ece5d66d6b4ed880a6220c55356f72a394bdf4f171b1eabc5a959156ec3abc9","sha256:cc80b854bdfa330288c7ff1be2deb91e6ed6b193ff6be02b1044b6669a82242d"],"state_sha256":"dfc751c91dbe1879349823945f79414cb36406632102db38246c2db123a96f42"}