{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O5X7H5Z6FXGM5ZY4XRZK3BRPRT","short_pith_number":"pith:O5X7H5Z6","canonical_record":{"source":{"id":"2003.03200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-03-06T13:40:44Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"cb2ee023048bf43dba43ef3660c9d624099e49f7aa3939b2d49bbe18f1da0285","abstract_canon_sha256":"c478b6721dde046828a32e226c5e080066ec7edb145aae8b09708b6acd10f7c1"},"schema_version":"1.0"},"canonical_sha256":"776ff3f73e2dcccee71cbc72ad862f8cf8366e0585dfc9e226b9cec3bf818168","source":{"kind":"arxiv","id":"2003.03200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03200","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03200v2","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03200","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"O5X7H5Z6FXGM","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"O5X7H5Z6FXGM5ZY4","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"O5X7H5Z6","created_at":"2026-07-05T00:56:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O5X7H5Z6FXGM5ZY4XRZK3BRPRT","target":"record","payload":{"canonical_record":{"source":{"id":"2003.03200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-03-06T13:40:44Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"cb2ee023048bf43dba43ef3660c9d624099e49f7aa3939b2d49bbe18f1da0285","abstract_canon_sha256":"c478b6721dde046828a32e226c5e080066ec7edb145aae8b09708b6acd10f7c1"},"schema_version":"1.0"},"canonical_sha256":"776ff3f73e2dcccee71cbc72ad862f8cf8366e0585dfc9e226b9cec3bf818168","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:56:03.475415Z","signature_b64":"hR42cl5FJFwg2MbQ1f5MnKW65iXzMPEbKwqweOga5ApBw1Cb9iikbZGs204zk/7eYnUPtSHg6KoLK8HOEuUbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"776ff3f73e2dcccee71cbc72ad862f8cf8366e0585dfc9e226b9cec3bf818168","last_reissued_at":"2026-07-05T00:56:03.474924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:56:03.474924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.03200","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYKrXxolueZA6bhdXJMqSfgFV5IJjJb+fvO6V5lJmdawxj/OK7BX5L66BysvVrWntMomiJeRxLUeaYXpU09fAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:13:33.079574Z"},"content_sha256":"d629d09809843e030d1bf9f7a1ad73d8691bfb2686b09fc5669e7bf7c6ea6bc2","schema_version":"1.0","event_id":"sha256:d629d09809843e030d1bf9f7a1ad73d8691bfb2686b09fc5669e7bf7c6ea6bc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O5X7H5Z6FXGM5ZY4XRZK3BRPRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.RO","authors_text":"David Hoeller, Marco Hutter, Miguel I. Valls, Napat Karnchanachari","submitted_at":"2020-03-06T13:40:44Z","abstract_excerpt":"Model Predictive Control (MPC) is a powerful control technique that handles constraints, takes the system's dynamics into account, and optimizes for a given cost function. In practice, however, it often requires an expert to craft and tune this cost function and find trade-offs between different state penalties to satisfy simple high level objectives. In this paper, we use Reinforcement Learning and in particular value learning to approximate the value function given only high level objectives, which can be sparse and binary. Building upon previous works, we present improvements that allowed u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03200","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.03200/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":"2026-07-05T00:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIhMA8BF2hk2H2F19ZQa+gurURSYzyfo/QvIHprRySfosidUrLkl/lsloRQJIJ4gbeQtmIOBTfF0oi50iahQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:13:33.080133Z"},"content_sha256":"fae7346bda5a0ccf729755c94bb14231c5e19c4ee9ef581646db21e3de59acb8","schema_version":"1.0","event_id":"sha256:fae7346bda5a0ccf729755c94bb14231c5e19c4ee9ef581646db21e3de59acb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/bundle.json","state_url":"https://pith.science/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/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":"2026-08-14T13:13:33Z","links":{"resolver":"https://pith.science/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT","bundle":"https://pith.science/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/bundle.json","state":"https://pith.science/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5X7H5Z6FXGM5ZY4XRZK3BRPRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O5X7H5Z6FXGM5ZY4XRZK3BRPRT","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":"c478b6721dde046828a32e226c5e080066ec7edb145aae8b09708b6acd10f7c1","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-03-06T13:40:44Z","title_canon_sha256":"cb2ee023048bf43dba43ef3660c9d624099e49f7aa3939b2d49bbe18f1da0285"},"schema_version":"1.0","source":{"id":"2003.03200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03200","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03200v2","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03200","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"O5X7H5Z6FXGM","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"O5X7H5Z6FXGM5ZY4","created_at":"2026-07-05T00:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"O5X7H5Z6","created_at":"2026-07-05T00:56:03Z"}],"graph_snapshots":[{"event_id":"sha256:fae7346bda5a0ccf729755c94bb14231c5e19c4ee9ef581646db21e3de59acb8","target":"graph","created_at":"2026-07-05T00:56:03Z","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/2003.03200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model Predictive Control (MPC) is a powerful control technique that handles constraints, takes the system's dynamics into account, and optimizes for a given cost function. In practice, however, it often requires an expert to craft and tune this cost function and find trade-offs between different state penalties to satisfy simple high level objectives. In this paper, we use Reinforcement Learning and in particular value learning to approximate the value function given only high level objectives, which can be sparse and binary. Building upon previous works, we present improvements that allowed u","authors_text":"David Hoeller, Marco Hutter, Miguel I. Valls, Napat Karnchanachari","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-03-06T13:40:44Z","title":"Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03200","kind":"arxiv","version":2},"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:d629d09809843e030d1bf9f7a1ad73d8691bfb2686b09fc5669e7bf7c6ea6bc2","target":"record","created_at":"2026-07-05T00:56:03Z","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":"c478b6721dde046828a32e226c5e080066ec7edb145aae8b09708b6acd10f7c1","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-03-06T13:40:44Z","title_canon_sha256":"cb2ee023048bf43dba43ef3660c9d624099e49f7aa3939b2d49bbe18f1da0285"},"schema_version":"1.0","source":{"id":"2003.03200","kind":"arxiv","version":2}},"canonical_sha256":"776ff3f73e2dcccee71cbc72ad862f8cf8366e0585dfc9e226b9cec3bf818168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"776ff3f73e2dcccee71cbc72ad862f8cf8366e0585dfc9e226b9cec3bf818168","first_computed_at":"2026-07-05T00:56:03.474924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:56:03.474924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hR42cl5FJFwg2MbQ1f5MnKW65iXzMPEbKwqweOga5ApBw1Cb9iikbZGs204zk/7eYnUPtSHg6KoLK8HOEuUbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:56:03.475415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d629d09809843e030d1bf9f7a1ad73d8691bfb2686b09fc5669e7bf7c6ea6bc2","sha256:fae7346bda5a0ccf729755c94bb14231c5e19c4ee9ef581646db21e3de59acb8"],"state_sha256":"20b4ce9897dbde785c1abe45cdaf5387837966389f4a834966f9c91180442f08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bm3CWPDlFYrMxbZw7U5OgKB0iAyjYjeSNGjRjtZmxTCMgkCxaJ4EwNeGVMWejZKC9WYDAA3YklT0R0geuMI2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:13:33.085882Z","bundle_sha256":"4b08d4e9dfddd8670e6eddc2b3c656e03e32e4f752ec785b9230b5cad4c41cd5"}}