{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5DQ2DFT2NPQAZQKWNHBBGLEB6D","short_pith_number":"pith:5DQ2DFT2","canonical_record":{"source":{"id":"2212.14066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T19:05:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3df33845cb03de6db10de6a1764f106ee50b700f87cbd483d8a0b0cbc503a6cc","abstract_canon_sha256":"884092108a98d8341fba5dd38e8907bd27ce6ac7adce6b947fd2806fb0ad66e1"},"schema_version":"1.0"},"canonical_sha256":"e8e1a1967a6be00cc15669c2132c81f0e3e54db1679568c7b905165252eccf76","source":{"kind":"arxiv","id":"2212.14066","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14066","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14066v2","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14066","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"5DQ2DFT2NPQA","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"5DQ2DFT2NPQAZQKW","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"5DQ2DFT2","created_at":"2026-07-05T05:31:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5DQ2DFT2NPQAZQKWNHBBGLEB6D","target":"record","payload":{"canonical_record":{"source":{"id":"2212.14066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T19:05:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3df33845cb03de6db10de6a1764f106ee50b700f87cbd483d8a0b0cbc503a6cc","abstract_canon_sha256":"884092108a98d8341fba5dd38e8907bd27ce6ac7adce6b947fd2806fb0ad66e1"},"schema_version":"1.0"},"canonical_sha256":"e8e1a1967a6be00cc15669c2132c81f0e3e54db1679568c7b905165252eccf76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:35.510436Z","signature_b64":"SZHWRri7gVJrLjsV+pDdDr/g4r/PwusGmme/6o49tXpIBcAIfsqkQcao1OsqooYz0ZOU0eq7BhW7MmtvIT6dAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e1a1967a6be00cc15669c2132c81f0e3e54db1679568c7b905165252eccf76","last_reissued_at":"2026-07-05T05:31:35.509955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:35.509955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.14066","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2INZ74YEhelFuar6WQvSNBcmy/uFk4CqVDUCW9ajtfCZCjU7a3qgv3gd+yWYP8C8ACFM31g3kFWIfzrii1SCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T05:27:26.200638Z"},"content_sha256":"ff2baf8b47c0b4a31956366b1e6071aecb51ea211daebfcb4e1ee36680145eb5","schema_version":"1.0","event_id":"sha256:ff2baf8b47c0b4a31956366b1e6071aecb51ea211daebfcb4e1ee36680145eb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5DQ2DFT2NPQAZQKWNHBBGLEB6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of Discounted Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Nota","submitted_at":"2022-12-28T19:05:41Z","abstract_excerpt":"Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is not the gradient of any objective function, little else is known about its convergence behavior or properties. In this paper, we show that if the discounted approximation is followed such that the discount factor is increased slowly at a rate related to a decreasing learning rate, the resulting method recovers the standard guarantees of gradient ascent on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14066","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/2212.14066/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:31:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hPwKHOSZj6VOlW04EHF0uPa5we5BtD3z1OgcsqjBf9FIw/tQ0p6CC9Urjld1z8b93HKTYazXjDRKVkRC9sndAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T05:27:26.201002Z"},"content_sha256":"72cf4085ea6959bd51e241f5d970d13dde98852d55496dc8dc29238e8704481a","schema_version":"1.0","event_id":"sha256:72cf4085ea6959bd51e241f5d970d13dde98852d55496dc8dc29238e8704481a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/bundle.json","state_url":"https://pith.science/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/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":"2026-07-19T05:27:26Z","links":{"resolver":"https://pith.science/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D","bundle":"https://pith.science/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/bundle.json","state":"https://pith.science/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DQ2DFT2NPQAZQKWNHBBGLEB6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5DQ2DFT2NPQAZQKWNHBBGLEB6D","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":"884092108a98d8341fba5dd38e8907bd27ce6ac7adce6b947fd2806fb0ad66e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T19:05:41Z","title_canon_sha256":"3df33845cb03de6db10de6a1764f106ee50b700f87cbd483d8a0b0cbc503a6cc"},"schema_version":"1.0","source":{"id":"2212.14066","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14066","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14066v2","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14066","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_12","alias_value":"5DQ2DFT2NPQA","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_16","alias_value":"5DQ2DFT2NPQAZQKW","created_at":"2026-07-05T05:31:35Z"},{"alias_kind":"pith_short_8","alias_value":"5DQ2DFT2","created_at":"2026-07-05T05:31:35Z"}],"graph_snapshots":[{"event_id":"sha256:72cf4085ea6959bd51e241f5d970d13dde98852d55496dc8dc29238e8704481a","target":"graph","created_at":"2026-07-05T05:31:35Z","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/2212.14066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many popular policy gradient methods for reinforcement learning follow a biased approximation of the policy gradient known as the discounted approximation. While it has been shown that the discounted approximation of the policy gradient is not the gradient of any objective function, little else is known about its convergence behavior or properties. In this paper, we show that if the discounted approximation is followed such that the discount factor is increased slowly at a rate related to a decreasing learning rate, the resulting method recovers the standard guarantees of gradient ascent on th","authors_text":"Chris Nota","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T19:05:41Z","title":"On the Convergence of Discounted Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14066","kind":"arxiv","version":2},"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:ff2baf8b47c0b4a31956366b1e6071aecb51ea211daebfcb4e1ee36680145eb5","target":"record","created_at":"2026-07-05T05:31:35Z","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":"884092108a98d8341fba5dd38e8907bd27ce6ac7adce6b947fd2806fb0ad66e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T19:05:41Z","title_canon_sha256":"3df33845cb03de6db10de6a1764f106ee50b700f87cbd483d8a0b0cbc503a6cc"},"schema_version":"1.0","source":{"id":"2212.14066","kind":"arxiv","version":2}},"canonical_sha256":"e8e1a1967a6be00cc15669c2132c81f0e3e54db1679568c7b905165252eccf76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8e1a1967a6be00cc15669c2132c81f0e3e54db1679568c7b905165252eccf76","first_computed_at":"2026-07-05T05:31:35.509955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:35.509955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SZHWRri7gVJrLjsV+pDdDr/g4r/PwusGmme/6o49tXpIBcAIfsqkQcao1OsqooYz0ZOU0eq7BhW7MmtvIT6dAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:35.510436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14066","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff2baf8b47c0b4a31956366b1e6071aecb51ea211daebfcb4e1ee36680145eb5","sha256:72cf4085ea6959bd51e241f5d970d13dde98852d55496dc8dc29238e8704481a"],"state_sha256":"1b49eb1d90a90a2afe1c3526d7ef4ccc84abcd6720e298fc5dbfe94d8b2a4262"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPZKKIDeMtoM8EOkdyXdW9ve5uCkUVI6zCugjIgftP/WCt9OUIwi6hNxmytJRvkJOg2d9TINEmq/Ty/7XDmJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T05:27:26.203130Z","bundle_sha256":"43c0d1b0bfa0802ee2763b897a9312404fffdbbe37afa9612b8f5db580e334a6"}}