{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AOVNQZGY6JYMVERPBZLMUAIALK","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":"8e54e3fe64a25439d9440c995a3cdf7b32f3b16497e4db3d10994464d6885ed5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T15:51:48Z","title_canon_sha256":"6a72d0d1bb0ba7484b98acd5efdd75e4e16cafef6a3a97956475c8c521931169"},"schema_version":"1.0","source":{"id":"2010.01069","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01069","created_at":"2026-07-05T03:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01069v4","created_at":"2026-07-05T03:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01069","created_at":"2026-07-05T03:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"AOVNQZGY6JYM","created_at":"2026-07-05T03:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"AOVNQZGY6JYMVERP","created_at":"2026-07-05T03:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"AOVNQZGY","created_at":"2026-07-05T03:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:407cb2b2d5c925a67d634cd07dbb5dad663ad716e972dce926a2ce478a89abe5","target":"graph","created_at":"2026-07-05T03:51:41Z","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/2010.01069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both actor and critic, i.e., there is a $\\gamma^t$ term in the actor update for the transition observed at time $t$ in a trajectory and the critic is a discounted value function. Practitioners, however, usually ignore the discounting ($\\gamma^t$) for the actor while using a discounted critic. We investigate this mismatch in two scenarios. In the first scenario, we consider optimizing an undiscounted obj","authors_text":"Harm van Seijen, Remi Tachet des Combes, Romain Laroche, Shangtong Zhang, Shimon Whiteson","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T15:51:48Z","title":"A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01069","kind":"arxiv","version":4},"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":"sha256:1a1b8ee779273d42d439aea3deff910d0da117497b7c092616fbb742f3633c3a","target":"record","created_at":"2026-07-05T03:51:41Z","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":"8e54e3fe64a25439d9440c995a3cdf7b32f3b16497e4db3d10994464d6885ed5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-02T15:51:48Z","title_canon_sha256":"6a72d0d1bb0ba7484b98acd5efdd75e4e16cafef6a3a97956475c8c521931169"},"schema_version":"1.0","source":{"id":"2010.01069","kind":"arxiv","version":4}},"canonical_sha256":"03aad864d8f270ca922f0e56ca01005aac4c7368fd390a451e205820781a9518","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03aad864d8f270ca922f0e56ca01005aac4c7368fd390a451e205820781a9518","first_computed_at":"2026-07-05T03:51:41.066462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:41.066462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqOJhTae+OmJ36coS/Ylxm1f/AGQLrKWdLyhTXEZ2i/ASNQp9aZa3LsXe/0zjiy33otQfG5JJHy70304G0iICg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:41.066930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.01069","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a1b8ee779273d42d439aea3deff910d0da117497b7c092616fbb742f3633c3a","sha256:407cb2b2d5c925a67d634cd07dbb5dad663ad716e972dce926a2ce478a89abe5"],"state_sha256":"a98c4d6d82199d867bdd7eeeb461e07ccf3eddfeb95ada540ace09b2041504d0"}