{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KZ3SOVG22RDHT2EBBKIE4CYMBK","short_pith_number":"pith:KZ3SOVG2","schema_version":"1.0","canonical_sha256":"56772754dad44679e8810a904e0b0c0aadf2bd59b42d4d86e11144b6c4b8b1fd","source":{"kind":"arxiv","id":"1901.10031","version":2},"attestation_state":"computed","paper":{"title":"Lyapunov-based Safe Policy Optimization for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","submitted_at":"2019-01-28T23:14:58Z","abstract_excerpt":"We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them. Our algorithms can use any standard policy gradient (PG) method, such as deep deterministic policy gradient (DDPG) or proximal policy optimization (PPO), to train a neural network policy, while gua"},"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":"1901.10031","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T23:14:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"56f65fa1946d192a1ef3f1220d030c1aa5f899b98cd5e62a4305046a18718b12","abstract_canon_sha256":"ce1150e08ad481b355ab5f168a0361ae57277470650ae0a4bfbbe9c5297520e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:15.113731Z","signature_b64":"sGQQSbRKABJpAQyF/Mh8DRwkTDY3Wz0KTXG22SvbO+hGggvm64al9Fzx6TKxEqCOBdngXWNuVAuZ06QCgC+yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56772754dad44679e8810a904e0b0c0aadf2bd59b42d4d86e11144b6c4b8b1fd","last_reissued_at":"2026-05-17T23:54:15.112763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:15.112763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lyapunov-based Safe Policy Optimization for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","submitted_at":"2019-01-28T23:14:58Z","abstract_excerpt":"We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them. Our algorithms can use any standard policy gradient (PG) method, such as deep deterministic policy gradient (DDPG) or proximal policy optimization (PPO), to train a neural network policy, while gua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10031","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1901.10031","created_at":"2026-05-17T23:54:15.113241+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10031v2","created_at":"2026-05-17T23:54:15.113241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10031","created_at":"2026-05-17T23:54:15.113241+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ3SOVG22RDH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ3SOVG22RDHT2EB","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ3SOVG2","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.12189","citing_title":"Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13662","citing_title":"Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2508.09128","citing_title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2601.06540","citing_title":"Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25379","citing_title":"Safe-Support Q-Learning: Learning without Unsafe Exploration","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12667","citing_title":"Safe reinforcement learning with online filtering for fatigue-predictive human-robot task planning and allocation in production","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK","json":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK.json","graph_json":"https://pith.science/api/pith-number/KZ3SOVG22RDHT2EBBKIE4CYMBK/graph.json","events_json":"https://pith.science/api/pith-number/KZ3SOVG22RDHT2EBBKIE4CYMBK/events.json","paper":"https://pith.science/paper/KZ3SOVG2"},"agent_actions":{"view_html":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK","download_json":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK.json","view_paper":"https://pith.science/paper/KZ3SOVG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10031&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ3SOVG22RDHT2EBBKIE4CYMBK/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ3SOVG22RDHT2EBBKIE4CYMBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK/action/storage_attestation","attest_author":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK/action/author_attestation","sign_citation":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK/action/citation_signature","submit_replication":"https://pith.science/pith/KZ3SOVG22RDHT2EBBKIE4CYMBK/action/replication_record"}},"created_at":"2026-05-17T23:54:15.113241+00:00","updated_at":"2026-05-17T23:54:15.113241+00:00"}