{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJLXTN46NXFNT7NTFIHVMNKISQ","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":"81b0809715909dcc6dd3896eda10e25cfb78cc43d9761845f09aca38f2978e86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:08:17Z","title_canon_sha256":"dd90965e4aa86b58ef3b6052a1cf853dbce886fbaff5221d6f902edd380dc68c"},"schema_version":"1.0","source":{"id":"2505.01336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01336","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01336v2","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01336","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"GJLXTN46NXFN","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"GJLXTN46NXFNT7NT","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"GJLXTN46","created_at":"2026-07-05T11:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:99fb827d4c0ce3b9c9cad41ca276547c596f3fd87e358213e43775392d6cf0bd","target":"graph","created_at":"2026-07-05T11:26:04Z","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/2505.01336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parallel data collection has redefined Reinforcement Learning (RL), unlocking unprecedented efficiency and powering breakthroughs in large-scale real-world applications. In this paradigm, $N$ identical agents operate in $N$ replicas of an environment simulator, accelerating data collection by a factor of $N$. A critical question arises: \\textit{Does specializing the policies of the parallel agents hold the key to surpass the $N$ factor acceleration?} In this paper, we introduce a novel learning framework that maximizes the entropy of collected data in a parallel setting. Our approach carefully","authors_text":"Marcello Restelli, Mirco Mutti, Riccardo Zamboni, Vincenzo De Paola","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:08:17Z","title":"Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01336","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":"sha256:5de3c1501831f110b868867ac61f96954b0c1f864631adb100c767b5c35560a9","target":"record","created_at":"2026-07-05T11:26:04Z","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":"81b0809715909dcc6dd3896eda10e25cfb78cc43d9761845f09aca38f2978e86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:08:17Z","title_canon_sha256":"dd90965e4aa86b58ef3b6052a1cf853dbce886fbaff5221d6f902edd380dc68c"},"schema_version":"1.0","source":{"id":"2505.01336","kind":"arxiv","version":2}},"canonical_sha256":"325779b79e6dcad9fdb32a0f56354894120556fa921297b8d664c2b84099dd5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"325779b79e6dcad9fdb32a0f56354894120556fa921297b8d664c2b84099dd5c","first_computed_at":"2026-07-05T11:26:04.069841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:04.069841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"81A3v85rFIaaaId/+v1UJ65H7EKZoUV1PM6hI639DlHAfDIi3UDGSqqj0qtZq0GGFgK0kEKoKQQiQm3Bdx6sBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:04.070295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5de3c1501831f110b868867ac61f96954b0c1f864631adb100c767b5c35560a9","sha256:99fb827d4c0ce3b9c9cad41ca276547c596f3fd87e358213e43775392d6cf0bd"],"state_sha256":"164555f0f0afdd2e1ffc2e91a7af935f2f36264fb91ec856424599928202b381"}