{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UOSDY3IR6M4G3UNNXXPCRATPOA","short_pith_number":"pith:UOSDY3IR","canonical_record":{"source":{"id":"2111.12953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T07:24:30Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"016120f5740489b62266c4a4b228de24f877bb9dee267c40b8ca96a1a7072ba4","abstract_canon_sha256":"510176af8a747c5f66b449b0eb2e23c2e342963007cf8a6096bc68519be3670b"},"schema_version":"1.0"},"canonical_sha256":"a3a43c6d11f3386dd1adbdde28826f700b024f4c806538a28201f4c25165171a","source":{"kind":"arxiv","id":"2111.12953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12953","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12953v1","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12953","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"UOSDY3IR6M4G","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"UOSDY3IR6M4G3UNN","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"UOSDY3IR","created_at":"2026-07-05T03:35:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UOSDY3IR6M4G3UNNXXPCRATPOA","target":"record","payload":{"canonical_record":{"source":{"id":"2111.12953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T07:24:30Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"016120f5740489b62266c4a4b228de24f877bb9dee267c40b8ca96a1a7072ba4","abstract_canon_sha256":"510176af8a747c5f66b449b0eb2e23c2e342963007cf8a6096bc68519be3670b"},"schema_version":"1.0"},"canonical_sha256":"a3a43c6d11f3386dd1adbdde28826f700b024f4c806538a28201f4c25165171a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:15.245113Z","signature_b64":"27gWMBPcEBcx/isNyqIl+wsJmXWKyYwaoFQpEgzyMjBHEK18rJYdLLTIFVoXWcFcaWKy6FBDegjT2QF0wBKnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a43c6d11f3386dd1adbdde28826f700b024f4c806538a28201f4c25165171a","last_reissued_at":"2026-07-05T03:35:15.244618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:15.244618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.12953","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":"2026-07-05T03:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DA6dnDzeZfwGkGwvQrJTfYQ03RYulkLzKi5Xmg04zcaNubY88pcsH4Y73hgWXRh7A39vAmR8Sc6EVQjoFmdWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:13:37.650210Z"},"content_sha256":"e32e36ff46403a8fd854051d6cf92afe599b72396a47842ce5675e448a5feb3f","schema_version":"1.0","event_id":"sha256:e32e36ff46403a8fd854051d6cf92afe599b72396a47842ce5675e448a5feb3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UOSDY3IR6M4G3UNNXXPCRATPOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Haitong Ma, Jianyu Chen, Shengbo Eben Li, Sifa Zheng, Wenchao Sun","submitted_at":"2021-11-25T07:24:30Z","abstract_excerpt":"In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger. This fact causes that the agent cannot learn a zero-violation policy even after convergence. Otherwise, it would not receive any penalty and lose the knowledge about danger. In this paper, we propose the safe set actor-critic (S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12953","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/2111.12953/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":"2026-07-05T03:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cmu7svSpmcoPhQuWPWbEfK2D2gHQfb8A0SXAgXXL2I2UAJixferAFuSQB3u3pTDgi39Gcti/cka8lJ4WYnefBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:13:37.650737Z"},"content_sha256":"1231c7619a82b4f21f19d17c597a0e5a892ec96b3dbee4398081abfd16bea178","schema_version":"1.0","event_id":"sha256:1231c7619a82b4f21f19d17c597a0e5a892ec96b3dbee4398081abfd16bea178"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/bundle.json","state_url":"https://pith.science/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/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":"2026-08-04T07:13:37Z","links":{"resolver":"https://pith.science/pith/UOSDY3IR6M4G3UNNXXPCRATPOA","bundle":"https://pith.science/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/bundle.json","state":"https://pith.science/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOSDY3IR6M4G3UNNXXPCRATPOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UOSDY3IR6M4G3UNNXXPCRATPOA","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":"510176af8a747c5f66b449b0eb2e23c2e342963007cf8a6096bc68519be3670b","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T07:24:30Z","title_canon_sha256":"016120f5740489b62266c4a4b228de24f877bb9dee267c40b8ca96a1a7072ba4"},"schema_version":"1.0","source":{"id":"2111.12953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12953","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12953v1","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12953","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"UOSDY3IR6M4G","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"UOSDY3IR6M4G3UNN","created_at":"2026-07-05T03:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"UOSDY3IR","created_at":"2026-07-05T03:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:1231c7619a82b4f21f19d17c597a0e5a892ec96b3dbee4398081abfd16bea178","target":"graph","created_at":"2026-07-05T03:35:15Z","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/2111.12953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger. This fact causes that the agent cannot learn a zero-violation policy even after convergence. Otherwise, it would not receive any penalty and lose the knowledge about danger. In this paper, we propose the safe set actor-critic (S","authors_text":"Changliu Liu, Haitong Ma, Jianyu Chen, Shengbo Eben Li, Sifa Zheng, Wenchao Sun","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T07:24:30Z","title":"Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12953","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:e32e36ff46403a8fd854051d6cf92afe599b72396a47842ce5675e448a5feb3f","target":"record","created_at":"2026-07-05T03:35:15Z","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":"510176af8a747c5f66b449b0eb2e23c2e342963007cf8a6096bc68519be3670b","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T07:24:30Z","title_canon_sha256":"016120f5740489b62266c4a4b228de24f877bb9dee267c40b8ca96a1a7072ba4"},"schema_version":"1.0","source":{"id":"2111.12953","kind":"arxiv","version":1}},"canonical_sha256":"a3a43c6d11f3386dd1adbdde28826f700b024f4c806538a28201f4c25165171a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a43c6d11f3386dd1adbdde28826f700b024f4c806538a28201f4c25165171a","first_computed_at":"2026-07-05T03:35:15.244618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:15.244618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"27gWMBPcEBcx/isNyqIl+wsJmXWKyYwaoFQpEgzyMjBHEK18rJYdLLTIFVoXWcFcaWKy6FBDegjT2QF0wBKnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:15.245113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e32e36ff46403a8fd854051d6cf92afe599b72396a47842ce5675e448a5feb3f","sha256:1231c7619a82b4f21f19d17c597a0e5a892ec96b3dbee4398081abfd16bea178"],"state_sha256":"ab0f3e2f4570ca8794d32a8ce13eb5d5c6beb0264c20d01c90e039d2e880b66c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BrWkqsANiWUtz5b4ltXq9XfY9GzRUYSR8lW6WWe6/EJU+mryA7TnWIWmgvmDyZTo6MNqHzvOkH+E8I4ZyceBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:13:37.656621Z","bundle_sha256":"b5d027a8b094f56891af7bd59ee68383ab9a74749d5441cd0b2c48faa7a38b3a"}}