{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:A6ZBQLVLJP7XM5NAY6562CE7BR","short_pith_number":"pith:A6ZBQLVL","canonical_record":{"source":{"id":"2303.02378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T10:52:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"033653a98df8c82065b6df36037997c845eaf92ff2b89c62198a0bbb21cf894a","abstract_canon_sha256":"61eeee59fb6abdb7d4c69828bd260eb836a2497cee97b03f9a92112dd2e5aaaa"},"schema_version":"1.0"},"canonical_sha256":"07b2182eab4bff7675a0c7bbed089f0c5b57b68041d098e463a329b505ad98a5","source":{"kind":"arxiv","id":"2303.02378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02378","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02378v1","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02378","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZBQLVLJP7X","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZBQLVLJP7XM5NA","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZBQLVL","created_at":"2026-07-05T05:48:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:A6ZBQLVLJP7XM5NAY6562CE7BR","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T10:52:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"033653a98df8c82065b6df36037997c845eaf92ff2b89c62198a0bbb21cf894a","abstract_canon_sha256":"61eeee59fb6abdb7d4c69828bd260eb836a2497cee97b03f9a92112dd2e5aaaa"},"schema_version":"1.0"},"canonical_sha256":"07b2182eab4bff7675a0c7bbed089f0c5b57b68041d098e463a329b505ad98a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:10.700106Z","signature_b64":"6ZV6HYuoWHT3/9r2RkiXxpmcw3At+nTO6WGbrBsWQp/j/9f8XtzWU1nXsH9yIoaWHaFNb/agEePhafUrAV6sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b2182eab4bff7675a0c7bbed089f0c5b57b68041d098e463a329b505ad98a5","last_reissued_at":"2026-07-05T05:48:10.699613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:10.699613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02378","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:48:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dCLiItmnW/N7ygntcFd0N8KOrjzKwiL1Fq8vdg4SFvh6shrbyW60iQXT6xYlzw7aBhYMmBHvlBWmA2zsaSiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:55:02.330251Z"},"content_sha256":"0478a978636290334bf587a1625f948d2a44ae18f9550fe359f0f05ec6e2fd6b","schema_version":"1.0","event_id":"sha256:0478a978636290334bf587a1625f948d2a44ae18f9550fe359f0f05ec6e2fd6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:A6ZBQLVLJP7XM5NAY6562CE7BR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli, Matteo Sacco","submitted_at":"2023-03-04T10:52:20Z","abstract_excerpt":"Uncertainty quantification has been extensively used as a means to achieve efficient directed exploration in Reinforcement Learning (RL). However, state-of-the-art methods for continuous actions still suffer from high sample complexity requirements. Indeed, they either completely lack strategies for propagating the epistemic uncertainty throughout the updates, or they mix it with aleatoric uncertainty while learning the full return distribution (e.g., distributional RL). In this paper, we propose Wasserstein Actor-Critic (WAC), an actor-critic architecture inspired by the recent Wasserstein Q-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02378","kind":"arxiv","version":1},"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/2303.02378/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":"2026-07-05T05:48:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGgNd2ZPCH/Mwr5oUAScguolN/iWx3Rkv38+5N+R6WdYcb9xM+fRS5khpGK3JyB+CnKvVFetad9vlarfsrSoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:55:02.330679Z"},"content_sha256":"569c99e3a01b463051cbe2e18840094e25dd4769843f3a5c9f4d9b573878423f","schema_version":"1.0","event_id":"sha256:569c99e3a01b463051cbe2e18840094e25dd4769843f3a5c9f4d9b573878423f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/bundle.json","state_url":"https://pith.science/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/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":"2026-08-17T15:55:02Z","links":{"resolver":"https://pith.science/pith/A6ZBQLVLJP7XM5NAY6562CE7BR","bundle":"https://pith.science/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/bundle.json","state":"https://pith.science/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6ZBQLVLJP7XM5NAY6562CE7BR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A6ZBQLVLJP7XM5NAY6562CE7BR","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":"61eeee59fb6abdb7d4c69828bd260eb836a2497cee97b03f9a92112dd2e5aaaa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T10:52:20Z","title_canon_sha256":"033653a98df8c82065b6df36037997c845eaf92ff2b89c62198a0bbb21cf894a"},"schema_version":"1.0","source":{"id":"2303.02378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02378","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02378v1","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02378","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZBQLVLJP7X","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZBQLVLJP7XM5NA","created_at":"2026-07-05T05:48:10Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZBQLVL","created_at":"2026-07-05T05:48:10Z"}],"graph_snapshots":[{"event_id":"sha256:569c99e3a01b463051cbe2e18840094e25dd4769843f3a5c9f4d9b573878423f","target":"graph","created_at":"2026-07-05T05:48:10Z","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/2303.02378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncertainty quantification has been extensively used as a means to achieve efficient directed exploration in Reinforcement Learning (RL). However, state-of-the-art methods for continuous actions still suffer from high sample complexity requirements. Indeed, they either completely lack strategies for propagating the epistemic uncertainty throughout the updates, or they mix it with aleatoric uncertainty while learning the full return distribution (e.g., distributional RL). In this paper, we propose Wasserstein Actor-Critic (WAC), an actor-critic architecture inspired by the recent Wasserstein Q-","authors_text":"Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli, Matteo Sacco","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T10:52:20Z","title":"Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02378","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":"sha256:0478a978636290334bf587a1625f948d2a44ae18f9550fe359f0f05ec6e2fd6b","target":"record","created_at":"2026-07-05T05:48:10Z","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":"61eeee59fb6abdb7d4c69828bd260eb836a2497cee97b03f9a92112dd2e5aaaa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T10:52:20Z","title_canon_sha256":"033653a98df8c82065b6df36037997c845eaf92ff2b89c62198a0bbb21cf894a"},"schema_version":"1.0","source":{"id":"2303.02378","kind":"arxiv","version":1}},"canonical_sha256":"07b2182eab4bff7675a0c7bbed089f0c5b57b68041d098e463a329b505ad98a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07b2182eab4bff7675a0c7bbed089f0c5b57b68041d098e463a329b505ad98a5","first_computed_at":"2026-07-05T05:48:10.699613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:10.699613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ZV6HYuoWHT3/9r2RkiXxpmcw3At+nTO6WGbrBsWQp/j/9f8XtzWU1nXsH9yIoaWHaFNb/agEePhafUrAV6sAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:10.700106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0478a978636290334bf587a1625f948d2a44ae18f9550fe359f0f05ec6e2fd6b","sha256:569c99e3a01b463051cbe2e18840094e25dd4769843f3a5c9f4d9b573878423f"],"state_sha256":"7a451ebea3f682ca66587d5067d30e019d420ca098f5aceb5bb2d141c6e625d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"so56m42u/vDZemy7Fbba6MEXi2xqo4IQNL5LMDrbLyUeajxfITpsDPDt7teGEzdXz2iVszRdWAvMPBncFWmfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:55:02.333907Z","bundle_sha256":"8efb99f08e9a3957915ab8a34da39014d95dd738b577f640f4aff550e724586e"}}