{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5KDMB4DJ5OK4TBMW46HRTCLMPL","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":"91587cba8299ad9ef7e814e9206dd567644eebf42ad1e23e3ab86c102ff89c03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T13:28:13Z","title_canon_sha256":"de699fcdc8ee8bc86111d296e2caf889e102f399759c7adfd0faacda380e4afb"},"schema_version":"1.0","source":{"id":"2111.15382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15382","created_at":"2026-07-05T03:36:25Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15382v1","created_at":"2026-07-05T03:36:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15382","created_at":"2026-07-05T03:36:25Z"},{"alias_kind":"pith_short_12","alias_value":"5KDMB4DJ5OK4","created_at":"2026-07-05T03:36:25Z"},{"alias_kind":"pith_short_16","alias_value":"5KDMB4DJ5OK4TBMW","created_at":"2026-07-05T03:36:25Z"},{"alias_kind":"pith_short_8","alias_value":"5KDMB4DJ","created_at":"2026-07-05T03:36:25Z"}],"graph_snapshots":[{"event_id":"sha256:cdfd13defd0597f66882bb8e709ccb9113c3ba5e46790aafbfff08aa3886ae01","target":"graph","created_at":"2026-07-05T03:36:25Z","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/2111.15382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growth of deep reinforcement learning (RL) has brought multiple exciting tools and methods to the field. This rapid expansion makes it important to understand the interplay between individual elements of the RL toolbox. We approach this task from an empirical perspective by conducting a study in the continuous control setting. We present multiple insights of fundamental nature, including: an average of multiple actors trained from the same data boosts performance; the existing methods are unstable across training runs, epochs of training, and evaluation runs; a commonly used additive actio","authors_text":"Jakub \\'Swi\\k{a}tkowski, {\\L}ukasz Kuci\\'nski, Marcin Andrychowicz, Mateusz Olko, Micha{\\l} Kr\\'olikowski, Piotr Januszewski, Piotr Mi{\\l}o\\'s","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T13:28:13Z","title":"Continuous Control With Ensemble Deep Deterministic Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15382","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":"sha256:6316db470f848c154dab71641d543aded832e8b967e406aac13517dc51f31980","target":"record","created_at":"2026-07-05T03:36:25Z","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":"91587cba8299ad9ef7e814e9206dd567644eebf42ad1e23e3ab86c102ff89c03","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T13:28:13Z","title_canon_sha256":"de699fcdc8ee8bc86111d296e2caf889e102f399759c7adfd0faacda380e4afb"},"schema_version":"1.0","source":{"id":"2111.15382","kind":"arxiv","version":1}},"canonical_sha256":"ea86c0f069eb95c98596e78f19896c7aff693e8d54309242f6242fe930b420ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea86c0f069eb95c98596e78f19896c7aff693e8d54309242f6242fe930b420ea","first_computed_at":"2026-07-05T03:36:25.612551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:25.612551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wNGI1WLWVUq1e+BS6ViDjaz2cXoYOcJf80BvrPzbXiujX7x9M136NRUIoFpPlyh0u7Fk2pikOyhU29/a5x/SAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:25.613026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6316db470f848c154dab71641d543aded832e8b967e406aac13517dc51f31980","sha256:cdfd13defd0597f66882bb8e709ccb9113c3ba5e46790aafbfff08aa3886ae01"],"state_sha256":"b8ddd5ac1dee659549c961951e13aa6208bc26472b8fa6d1dc931f1c804722d5"}