{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B4HKMTAA2CBYQNGI7WGCTGJT65","short_pith_number":"pith:B4HKMTAA","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"},"canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","source":{"kind":"arxiv","id":"2309.15430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15430","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15430v1","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15430","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"B4HKMTAA2CBY","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"B4HKMTAA2CBYQNGI","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"B4HKMTAA","created_at":"2026-07-05T06:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B4HKMTAA2CBYQNGI7WGCTGJT65","target":"record","payload":{"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"},"canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","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"},"source_kind":"arxiv","source_id":"2309.15430","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":"2026-07-05T06:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yM57JvhvfVdLXFYm1iXAKBbi2+C1QKJsJlLgh6/Yhro75MhTHKYcTN8ixlCF5Hds2votFDo1zm3VILWUbYsTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:13:25.329713Z"},"content_sha256":"ac23d77abaef072b40866eac8743927154ba02351db376e9ec8d1481adbae3b4","schema_version":"1.0","event_id":"sha256:ac23d77abaef072b40866eac8743927154ba02351db376e9ec8d1481adbae3b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B4HKMTAA2CBYQNGI7WGCTGJT65","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qaz6Utsrb7+7ueiGG/i0ctQizi/amMlQyJ8xZX4ZIJgHaQHTd2/yHuqP+WiDohglD3heX5nAdFz0Puvb8p9KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:13:25.330480Z"},"content_sha256":"643c0831135a261af3dab292ff8a2bd4a5478d2596e1cb792c9c509cd526a7cf","schema_version":"1.0","event_id":"sha256:643c0831135a261af3dab292ff8a2bd4a5478d2596e1cb792c9c509cd526a7cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/bundle.json","state_url":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/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":"2026-08-10T19:13:25Z","links":{"resolver":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65","bundle":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/bundle.json","state":"https://pith.science/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4HKMTAA2CBYQNGI7WGCTGJT65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B4HKMTAA2CBYQNGI7WGCTGJT65","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":"e535a885c84e9764c654339773898ce96e1fbcc4307204d62b3ff05b9d2f58e6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T06:49:20Z","title_canon_sha256":"c7a914d19f1b86edbc8d187ef93636eebb6e696d012862baa4a1396e4db48df5"},"schema_version":"1.0","source":{"id":"2309.15430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15430","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15430v1","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15430","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"B4HKMTAA2CBY","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"B4HKMTAA2CBYQNGI","created_at":"2026-07-05T06:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"B4HKMTAA","created_at":"2026-07-05T06:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:643c0831135a261af3dab292ff8a2bd4a5478d2596e1cb792c9c509cd526a7cf","target":"graph","created_at":"2026-07-05T06:54:45Z","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/2309.15430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Reske, Joonho Lee, Lukas Schroth, Marco Hutter, Marko Bjelonic, Victor Klemm","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T06:49:20Z","title":"Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15430","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:ac23d77abaef072b40866eac8743927154ba02351db376e9ec8d1481adbae3b4","target":"record","created_at":"2026-07-05T06:54:45Z","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":"e535a885c84e9764c654339773898ce96e1fbcc4307204d62b3ff05b9d2f58e6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T06:49:20Z","title_canon_sha256":"c7a914d19f1b86edbc8d187ef93636eebb6e696d012862baa4a1396e4db48df5"},"schema_version":"1.0","source":{"id":"2309.15430","kind":"arxiv","version":1}},"canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f0ea64c00d0838834c8fd8c299933f77c48923466f755df02c26bf3d91c29d2","first_computed_at":"2026-07-05T06:54:45.781385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:45.781385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dyuoFkJ/aA69WHNfMSywkBxJw0CXwbBWy9wlY9EGb5zqUpRdmExlW/jzAOp7A8hbol8AYT7n/tLfKXxwKEx8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:45.781809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac23d77abaef072b40866eac8743927154ba02351db376e9ec8d1481adbae3b4","sha256:643c0831135a261af3dab292ff8a2bd4a5478d2596e1cb792c9c509cd526a7cf"],"state_sha256":"a93ee152bb6ef0ed277bb10544d2c2df621791966c2172c5e8838ae9bf13eeab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhUOyPiM+wbcud2w8024RJasxBFLKoWxuhqgcqHeCmheqU6sVbBVKTszCHzrPZNAZPw54OVtRF++oC0LH2LOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:13:25.336846Z","bundle_sha256":"37554dbee70259e2984d1d7aa64edc0e7e36032b4a8111d12ed18e52f1ab41dc"}}