{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZUBX3BM2VPKX7VGFGOGWSOF7WB","short_pith_number":"pith:ZUBX3BM2","canonical_record":{"source":{"id":"1611.01055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T15:15:00Z","cross_cats_sorted":["cs.GR","cs.RO"],"title_canon_sha256":"c0aa95a4f00a2a1e903be84ec7684a32ec2add1f97668a0b6abe7df8152e6097","abstract_canon_sha256":"16e7f75ae340469c6bc5b2ef0315812a25c594a77a9b9ecb3335715cff3a759c"},"schema_version":"1.0"},"canonical_sha256":"cd037d859aabd57fd4c5338d6938bfb064ffea7ba277dfff56f3ae1908b3e996","source":{"kind":"arxiv","id":"1611.01055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01055","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01055v1","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01055","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZUBX3BM2VPKX","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZUBX3BM2VPKX7VGF","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZUBX3BM2","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZUBX3BM2VPKX7VGFGOGWSOF7WB","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T15:15:00Z","cross_cats_sorted":["cs.GR","cs.RO"],"title_canon_sha256":"c0aa95a4f00a2a1e903be84ec7684a32ec2add1f97668a0b6abe7df8152e6097","abstract_canon_sha256":"16e7f75ae340469c6bc5b2ef0315812a25c594a77a9b9ecb3335715cff3a759c"},"schema_version":"1.0"},"canonical_sha256":"cd037d859aabd57fd4c5338d6938bfb064ffea7ba277dfff56f3ae1908b3e996","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:31.247586Z","signature_b64":"30W1SvnA9V04CpJoTg1nLEC03AUu80AlxTStnrM+af0ov7VS/Z5h0mKcvlBC/zBYFk1JkGFTLXhkT+Tkk6Z4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd037d859aabd57fd4c5338d6938bfb064ffea7ba277dfff56f3ae1908b3e996","last_reissued_at":"2026-05-18T00:32:31.246877Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:31.246877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01055","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":"2026-05-18T00:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmeYsKmcQQTTNQi9v8TcL0fh9z35Qbxlp/2QnmADarmzLprQwqI8xg7IbxJiRSh5VybXmkQc4DY1E3230Q4zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:46:35.391352Z"},"content_sha256":"d36c8597901fd98ab8a22004bbea519d232ab955b60875395ed8c7bf80fef256","schema_version":"1.0","event_id":"sha256:d36c8597901fd98ab8a22004bbea519d232ab955b60875395ed8c7bf80fef256"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZUBX3BM2VPKX7VGFGOGWSOF7WB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.RO"],"primary_cat":"cs.LG","authors_text":"Michiel van de Panne, Xue Bin Peng","submitted_at":"2016-11-03T15:15:00Z","abstract_excerpt":"The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance. We compare the impact of four different action parameterizations (torques, muscle-activations, target joint angles, and target joint-angle velocities) in terms of learning time, policy robustness, motion quality, and policy query rates. Our results are evaluated on a gait-cycle imitation task for multiple planar articulated figures and multiple gaits. We demonstrate that the local f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01055","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":""},"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":"2026-05-18T00:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHxxyP6TqBfIWm7T4Vl4/XwEW8vRNiEfLr9gbrdXZttAfODQxbpaap33Mwz5WtiajQJ91ZDPIRoHIkhYLQdVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:46:35.391767Z"},"content_sha256":"06ecbd8ee616cd4bc0d9575793c889c4f3944196d0f523822c1846ca4389fbb8","schema_version":"1.0","event_id":"sha256:06ecbd8ee616cd4bc0d9575793c889c4f3944196d0f523822c1846ca4389fbb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/bundle.json","state_url":"https://pith.science/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/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":"2026-05-30T08:46:35Z","links":{"resolver":"https://pith.science/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB","bundle":"https://pith.science/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/bundle.json","state":"https://pith.science/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZUBX3BM2VPKX7VGFGOGWSOF7WB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZUBX3BM2VPKX7VGFGOGWSOF7WB","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":"16e7f75ae340469c6bc5b2ef0315812a25c594a77a9b9ecb3335715cff3a759c","cross_cats_sorted":["cs.GR","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T15:15:00Z","title_canon_sha256":"c0aa95a4f00a2a1e903be84ec7684a32ec2add1f97668a0b6abe7df8152e6097"},"schema_version":"1.0","source":{"id":"1611.01055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01055","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01055v1","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01055","created_at":"2026-05-18T00:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZUBX3BM2VPKX","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZUBX3BM2VPKX7VGF","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZUBX3BM2","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:06ecbd8ee616cd4bc0d9575793c889c4f3944196d0f523822c1846ca4389fbb8","target":"graph","created_at":"2026-05-18T00:32:31Z","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"},"paper":{"abstract_excerpt":"The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance. We compare the impact of four different action parameterizations (torques, muscle-activations, target joint angles, and target joint-angle velocities) in terms of learning time, policy robustness, motion quality, and policy query rates. Our results are evaluated on a gait-cycle imitation task for multiple planar articulated figures and multiple gaits. We demonstrate that the local f","authors_text":"Michiel van de Panne, Xue Bin Peng","cross_cats":["cs.GR","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T15:15:00Z","title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01055","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:d36c8597901fd98ab8a22004bbea519d232ab955b60875395ed8c7bf80fef256","target":"record","created_at":"2026-05-18T00:32:31Z","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":"16e7f75ae340469c6bc5b2ef0315812a25c594a77a9b9ecb3335715cff3a759c","cross_cats_sorted":["cs.GR","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-03T15:15:00Z","title_canon_sha256":"c0aa95a4f00a2a1e903be84ec7684a32ec2add1f97668a0b6abe7df8152e6097"},"schema_version":"1.0","source":{"id":"1611.01055","kind":"arxiv","version":1}},"canonical_sha256":"cd037d859aabd57fd4c5338d6938bfb064ffea7ba277dfff56f3ae1908b3e996","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd037d859aabd57fd4c5338d6938bfb064ffea7ba277dfff56f3ae1908b3e996","first_computed_at":"2026-05-18T00:32:31.246877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:31.246877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"30W1SvnA9V04CpJoTg1nLEC03AUu80AlxTStnrM+af0ov7VS/Z5h0mKcvlBC/zBYFk1JkGFTLXhkT+Tkk6Z4BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:31.247586Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d36c8597901fd98ab8a22004bbea519d232ab955b60875395ed8c7bf80fef256","sha256:06ecbd8ee616cd4bc0d9575793c889c4f3944196d0f523822c1846ca4389fbb8"],"state_sha256":"c1b0a0c9983fead89f797005e150b211a1b69c6d1a4d17e372c3b2c072c6ad79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tET597n1oqrT6fSR4v11/3KF/yv8bpDI4ICtqbgetYdH0hhlcj8yD/Aag/RE4/7GCq41Akg857dcoXu5N7QgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:46:35.398269Z","bundle_sha256":"3cdb93968f1144cd9f7a96383afaac45ca66b04b4939c35312afb7167aaa9ade"}}