{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LUOEGFC2RZPV5J5QNSYA5EL433","short_pith_number":"pith:LUOEGFC2","schema_version":"1.0","canonical_sha256":"5d1c43145a8e5f5ea7b06cb00e917cdeed35476e44d30c0dd50afadd03fc6674","source":{"kind":"arxiv","id":"2010.03152","version":1},"attestation_state":"computed","paper":{"title":"Projection-Based Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge, Tsung-Yen Yang","submitted_at":"2020-10-07T04:22:45Z","abstract_excerpt":"We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy Optimization (PCPO). This is an iterative method for optimizing policies in a two-step process: the first step performs a local reward improvement update, while the second step reconciles any constraint violation by projecting the policy back onto the constraint set. We theoretically analyze PCPO and provide a lower bound on reward improvement, and an upper bou"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.03152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:22:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"eebc27bb4963abc7aefe03cf28989896a06f4e9286bf33d05800307205d9f03c","abstract_canon_sha256":"dc2f62e9ae4b93004efbf4ffe84b33b6eac3f801256cb5849b5e93c42a80a11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:00.362467Z","signature_b64":"jkTGv9IAS2kyaTQs0xRyrQiPxqvcVApJ0Hkg96Cvw6lGesbsgH9wxbppq/qkyLtvWdIxeiUuRtKIjFYln52OAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d1c43145a8e5f5ea7b06cb00e917cdeed35476e44d30c0dd50afadd03fc6674","last_reissued_at":"2026-07-05T01:41:00.361998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:00.361998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projection-Based Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge, Tsung-Yen Yang","submitted_at":"2020-10-07T04:22:45Z","abstract_excerpt":"We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy Optimization (PCPO). This is an iterative method for optimizing policies in a two-step process: the first step performs a local reward improvement update, while the second step reconciles any constraint violation by projecting the policy back onto the constraint set. We theoretically analyze PCPO and provide a lower bound on reward improvement, and an upper bou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03152","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/2010.03152/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.03152","created_at":"2026-07-05T01:41:00.362052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03152v1","created_at":"2026-07-05T01:41:00.362052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03152","created_at":"2026-07-05T01:41:00.362052+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUOEGFC2RZPV","created_at":"2026-07-05T01:41:00.362052+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUOEGFC2RZPV5J5Q","created_at":"2026-07-05T01:41:00.362052+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUOEGFC2","created_at":"2026-07-05T01:41:00.362052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22579","citing_title":"Stationary Robust Mean-Field Games under Model Mismatches","ref_index":193,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28217","citing_title":"Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27861","citing_title":"PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11975","citing_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06600","citing_title":"Learning Reachability of Energy Storage Arbitrage","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14174","citing_title":"Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14246","citing_title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11688","citing_title":"Shaping Zero-Shot Coordination via State Blocking","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11975","citing_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433","json":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433.json","graph_json":"https://pith.science/api/pith-number/LUOEGFC2RZPV5J5QNSYA5EL433/graph.json","events_json":"https://pith.science/api/pith-number/LUOEGFC2RZPV5J5QNSYA5EL433/events.json","paper":"https://pith.science/paper/LUOEGFC2"},"agent_actions":{"view_html":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433","download_json":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433.json","view_paper":"https://pith.science/paper/LUOEGFC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03152&json=true","fetch_graph":"https://pith.science/api/pith-number/LUOEGFC2RZPV5J5QNSYA5EL433/graph.json","fetch_events":"https://pith.science/api/pith-number/LUOEGFC2RZPV5J5QNSYA5EL433/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433/action/storage_attestation","attest_author":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433/action/author_attestation","sign_citation":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433/action/citation_signature","submit_replication":"https://pith.science/pith/LUOEGFC2RZPV5J5QNSYA5EL433/action/replication_record"}},"created_at":"2026-07-05T01:41:00.362052+00:00","updated_at":"2026-07-05T01:41:00.362052+00:00"}