{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B4HKMTAA2CBYQNGI7WGCTGJT65","short_pith_number":"pith:B4HKMTAA","schema_version":"1.0","canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","source":{"kind":"arxiv","id":"2309.15430","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alexander Reske, Joonho Lee, Lukas Schroth, Marco Hutter, Marko Bjelonic, Victor Klemm","submitted_at":"2023-09-27T06:49:20Z","abstract_excerpt":"Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical constraints during training. While high-fidelity simulations provide significant benefits, they often bypass these essential physical limitations. In this paper, we experiment with the Constrained Markov Decision Process (CMDP) framework instead of the conventional unconstrained RL for robotic applications. We perform a comparative study of different constrained policy optimization algorithms to identify suitable methods fo"},"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":"2309.15430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T06:49:20Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"c7a914d19f1b86edbc8d187ef93636eebb6e696d012862baa4a1396e4db48df5","abstract_canon_sha256":"e535a885c84e9764c654339773898ce96e1fbcc4307204d62b3ff05b9d2f58e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:45.781809Z","signature_b64":"dyuoFkJ/aA69WHNfMSywkBxJw0CXwbBWy9wlY9EGb5zqUpRdmExlW/jzAOp7A8hbol8AYT7n/tLfKXxwKEx8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","last_reissued_at":"2026-07-05T06:54:45.781385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:45.781385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alexander Reske, Joonho Lee, Lukas Schroth, Marco Hutter, Marko Bjelonic, Victor Klemm","submitted_at":"2023-09-27T06:49:20Z","abstract_excerpt":"Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical constraints during training. While high-fidelity simulations provide significant benefits, they often bypass these essential physical limitations. In this paper, we experiment with the Constrained Markov Decision Process (CMDP) framework instead of the conventional unconstrained RL for robotic applications. We perform a comparative study of different constrained policy optimization algorithms to identify suitable methods fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15430","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/2309.15430/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":"2309.15430","created_at":"2026-07-05T06:54:45.781443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15430v1","created_at":"2026-07-05T06:54:45.781443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15430","created_at":"2026-07-05T06:54:45.781443+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4HKMTAA2CBY","created_at":"2026-07-05T06:54:45.781443+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4HKMTAA2CBYQNGI","created_at":"2026-07-05T06:54:45.781443+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4HKMTAA","created_at":"2026-07-05T06:54:45.781443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.06571","citing_title":"Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65","json":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65.json","graph_json":"https://pith.science/api/pith-number/B4HKMTAA2CBYQNGI7WGCTGJT65/graph.json","events_json":"https://pith.science/api/pith-number/B4HKMTAA2CBYQNGI7WGCTGJT65/events.json","paper":"https://pith.science/paper/B4HKMTAA"},"agent_actions":{"view_html":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65","download_json":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65.json","view_paper":"https://pith.science/paper/B4HKMTAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15430&json=true","fetch_graph":"https://pith.science/api/pith-number/B4HKMTAA2CBYQNGI7WGCTGJT65/graph.json","fetch_events":"https://pith.science/api/pith-number/B4HKMTAA2CBYQNGI7WGCTGJT65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/action/storage_attestation","attest_author":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/action/author_attestation","sign_citation":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/action/citation_signature","submit_replication":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/action/replication_record"}},"created_at":"2026-07-05T06:54:45.781443+00:00","updated_at":"2026-07-05T06:54:45.781443+00:00"}