{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U54A2USE5AAUYLTYEDF7RQIAQH","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":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7"},"schema_version":"1.0","source":{"id":"2304.08743","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08743v2","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08743","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"U54A2USE5AAU","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"U54A2USE5AAUYLTY","created_at":"2026-07-05T06:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"U54A2USE","created_at":"2026-07-05T06:26:01Z"}],"graph_snapshots":[{"event_id":"sha256:8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4","target":"graph","created_at":"2026-07-05T06:26:01Z","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/2304.08743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a s","authors_text":"Kazumi Kasaura, Kenta Hoshino, Ryo Yonetani, Shuwa Miura, Tadashi Kozuno, Yohei Hosoe","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title":"Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08743","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":"sha256:0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe","target":"record","created_at":"2026-07-05T06:26:01Z","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":"c7c7dcb8d736fe160142f04507978be3668db893ae31e80e9c54b461c8381fbe","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-18T05:45:09Z","title_canon_sha256":"f89a101b339ec5b23377ded41c6394d1af6d4fb6b72127a60d44ff14431d4ac7"},"schema_version":"1.0","source":{"id":"2304.08743","kind":"arxiv","version":2}},"canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7780d5244e8014c2e7820cbf8c10081e9f4d4ba8731acaa3cc411a3e2b6ded1","first_computed_at":"2026-07-05T06:26:01.801935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:01.801935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dLS1Hn/fvHPHGmqkQ0nCZMYB13+UcITCVeJSPT+Fj21Pm8aEJjg4FNuJ+ENTTf7WiaSKx+cGWSXlzZJLDsSdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:01.802370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08743","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fc8571b12bf306a57d7ef075cbb6b0f2b020883591b81a7ace2d3a01be265fe","sha256:8085161f527ab267f261893981d516d96229fd8b85cac92843328dbbd7f016e4"],"state_sha256":"a86567f82e7eff919d52dd226f245032962e30e8735b705e9ee9958dc75ac6d3"}