{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3O2NW6MUWRIQI5AYEPYI2GI3VH","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":"5955861aff54f4a26f19eb8525f39040a23221f3341e72bedce84adf277ce32b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T15:42:15Z","title_canon_sha256":"db4b5f8366ac4a8af60d29f80e51e20e04b6e5f049aecf7974c6f59b23dd1148"},"schema_version":"1.0","source":{"id":"2506.06178","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06178","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06178v3","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06178","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"3O2NW6MUWRIQ","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"3O2NW6MUWRIQI5AY","created_at":"2026-06-04T01:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"3O2NW6MU","created_at":"2026-06-04T01:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:5d31fd4a66e3863066ea0efadd24d1b13b137fecc4285872487bacb898bc6403","target":"graph","created_at":"2026-06-04T01:08:29Z","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/2506.06178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. They rely on fresh on-policy data, making them sample-inefficient and requiring $O(\\epsilon^{-2})$ trajectories to reach an $\\epsilon$-approximate stationary point. A common strategy to improve efficiency is to reuse information from past iterations, such as previous gradients or trajectories, leading to off-policy PG methods. While gradient reuse has received substantial attention, leading to improved rates up to $O(\\epsilon^{-3/2})$, the reuse o","authors_text":"Alberto Maria Metelli, Alessandro Montenegro, Federico Mansutti, Marco Mussi, Matteo Papini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T15:42:15Z","title":"Reusing Trajectories in Policy Gradients Enables Fast Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06178","kind":"arxiv","version":3},"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:c062c379871221866caefcafea414deec2ca9147b748295949b7f051dfe08e91","target":"record","created_at":"2026-06-04T01:08:29Z","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":"5955861aff54f4a26f19eb8525f39040a23221f3341e72bedce84adf277ce32b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T15:42:15Z","title_canon_sha256":"db4b5f8366ac4a8af60d29f80e51e20e04b6e5f049aecf7974c6f59b23dd1148"},"schema_version":"1.0","source":{"id":"2506.06178","kind":"arxiv","version":3}},"canonical_sha256":"dbb4db7994b45104741823f08d191ba9fda5ac9b52b046ea74714833b2bb337b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbb4db7994b45104741823f08d191ba9fda5ac9b52b046ea74714833b2bb337b","first_computed_at":"2026-06-04T01:08:29.736029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:29.736029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aT9oYEgX3jG8xc/S8Bb9oqWpteYViOCOpnTI1SLNds/JtI9Wo6CBorY+Onw78lUODUU6ifGISfQGy3O7hR8oDw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:29.736573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06178","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c062c379871221866caefcafea414deec2ca9147b748295949b7f051dfe08e91","sha256:5d31fd4a66e3863066ea0efadd24d1b13b137fecc4285872487bacb898bc6403"],"state_sha256":"4dce130ba70d5f977a06db8be6142c96cec4bd00a5fdd3c0da52cda2ef77b855"}