{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LGTZJMBHE6ZQVDBCBT7HNPFRII","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":"d06b6da6d881a666161be1acd4cf1c4934c8cef0c8bb333bd6a261c2867724ac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-21T00:10:29Z","title_canon_sha256":"537075ec88e8e206019edd8f80881483a7a87bda381de724edaff0d53b807ad1"},"schema_version":"1.0","source":{"id":"2003.09534","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.09534","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2003.09534v4","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09534","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"LGTZJMBHE6ZQ","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"LGTZJMBHE6ZQVDBC","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"LGTZJMBH","created_at":"2026-07-05T01:27:22Z"}],"graph_snapshots":[{"event_id":"sha256:39facbf9e581995d84b5ba6c85e48252256c4ceffaafa2ba9ca7991d314c74cd","target":"graph","created_at":"2026-07-05T01:27:22Z","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/2003.09534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) has achieved great empirical successes in various domains. However, the large search space of neural networks requires a large amount of data, which makes the current RL algorithms not sample efficient. Motivated by the fact that many environments with continuous state space have smooth transitions, we propose to learn a smooth policy that behaves smoothly with respect to states. We develop a new framework -- \\textbf{S}mooth \\textbf{R}egularized \\textbf{R}einforcement \\textbf{L}earning ($\\textbf{SR}^2\\textbf{L}$), where the policy is trained with smoothness-ind","authors_text":"Haoming Jiang, Qianli Shen, Tuo Zhao, Yan Li, Zhaoran Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-21T00:10:29Z","title":"Deep Reinforcement Learning with Robust and Smooth Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09534","kind":"arxiv","version":4},"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":"sha256:0a9c85ddfa75d700833a7fa7a8d9f3ec10690ac2b5f68f09851bd2813ef7e95a","target":"record","created_at":"2026-07-05T01:27:22Z","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":"d06b6da6d881a666161be1acd4cf1c4934c8cef0c8bb333bd6a261c2867724ac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-21T00:10:29Z","title_canon_sha256":"537075ec88e8e206019edd8f80881483a7a87bda381de724edaff0d53b807ad1"},"schema_version":"1.0","source":{"id":"2003.09534","kind":"arxiv","version":4}},"canonical_sha256":"59a794b02727b30a8c220cfe76bcb14226a1df18b5e6bae5016cc2fcb07f42fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59a794b02727b30a8c220cfe76bcb14226a1df18b5e6bae5016cc2fcb07f42fe","first_computed_at":"2026-07-05T01:27:22.022234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:22.022234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q6MA61+B9ISpibODY8IlS+y7eH8yDFULO1DYGn1qMuowbbEy4zjdA4jznl27OH8rxuTH3LOdCAX1wQl97colAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:22.022756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.09534","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a9c85ddfa75d700833a7fa7a8d9f3ec10690ac2b5f68f09851bd2813ef7e95a","sha256:39facbf9e581995d84b5ba6c85e48252256c4ceffaafa2ba9ca7991d314c74cd"],"state_sha256":"bc5d7a570e4b85a7db75c2532bdefe2123ccccf314271a0b078846a08353675c"}