{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NEM5WZEBQADM3QQ4JXH2NR3ZNY","short_pith_number":"pith:NEM5WZEB","canonical_record":{"source":{"id":"1903.06282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:13:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"71f0dd86417ff1418df82f88eb9317c25420aced9b8c4785e8ef334c68cc6f83","abstract_canon_sha256":"54167dc6885648d5e78a5736152affda988819c0b4b275a85015b01970460f9b"},"schema_version":"1.0"},"canonical_sha256":"6919db64818006cdc21c4dcfa6c7796e2ec688bc1a3764c3c594f1d8248f4d33","source":{"kind":"arxiv","id":"1903.06282","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06282","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06282v2","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06282","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"NEM5WZEBQADM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NEM5WZEBQADM3QQ4","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NEM5WZEB","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NEM5WZEBQADM3QQ4JXH2NR3ZNY","target":"record","payload":{"canonical_record":{"source":{"id":"1903.06282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:13:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"71f0dd86417ff1418df82f88eb9317c25420aced9b8c4785e8ef334c68cc6f83","abstract_canon_sha256":"54167dc6885648d5e78a5736152affda988819c0b4b275a85015b01970460f9b"},"schema_version":"1.0"},"canonical_sha256":"6919db64818006cdc21c4dcfa6c7796e2ec688bc1a3764c3c594f1d8248f4d33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.725806Z","signature_b64":"Pvz9lLOdiVC51eD2qjTD7DVYA61u5Zv2Ij8XRw/Ulichy/EpYV5486WYNU0MEq9GKWdOwitQjwkiQ8gj21u0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6919db64818006cdc21c4dcfa6c7796e2ec688bc1a3764c3c594f1d8248f4d33","last_reissued_at":"2026-05-17T23:51:04.725222Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.725222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.06282","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":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGkSEi6CYJtMmQ7ImbEt5YN2JDFHjAIjHB1eCSQn6Kf8QZDA+AnKVSHvVe1VJWOXG2lP3dS1gcGb5Mhos+2DCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:18:58.675164Z"},"content_sha256":"696de4d5bbd831259de39e4faa61f55479917972632e38440157330f429e9bca","schema_version":"1.0","event_id":"sha256:696de4d5bbd831259de39e4faa61f55479917972632e38440157330f429e9bca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NEM5WZEBQADM3QQ4JXH2NR3ZNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROS2Learn: a reinforcement learning framework for ROS 2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alejandro Solano Rueda, Elias Barba Moral, Lander Usategui San Juan, Nestor Gonzalez Lopez, Risto Kojcev, V\\'ictor Mayoral Vilches, Yue Leire Erro Nuin","submitted_at":"2019-03-14T22:13:23Z","abstract_excerpt":"We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics to train a robot directly from joint states, using traditional robotic tools. We use an state-of-the-art implementation of the Proximal Policy Optimization, Trust Region Policy Optimization and Actor-Critic Kronecker-Factored Trust Region algorithms to learn policies in four different Modular Articulated Robotic Arm (MARA) environments. We support this process using a framework that communicates with typical tools used in robotics, such as Gazebo and Robot Operating System 2 (ROS 2). We evaluate several algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06282","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnA8yTmE+oucDExPTmwFD0+nLjBelMn3sxbJidhePRZy34c6Qzpse97jXQrjVZAJeIURqktxvMV7WrUTKK/eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:18:58.675785Z"},"content_sha256":"7172911299548fd56a90e083c0edaa3e1680eddd9439b1ba155acdc3666c10f6","schema_version":"1.0","event_id":"sha256:7172911299548fd56a90e083c0edaa3e1680eddd9439b1ba155acdc3666c10f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/bundle.json","state_url":"https://pith.science/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/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":"2026-06-07T08:18:58Z","links":{"resolver":"https://pith.science/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY","bundle":"https://pith.science/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/bundle.json","state":"https://pith.science/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NEM5WZEBQADM3QQ4JXH2NR3ZNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NEM5WZEBQADM3QQ4JXH2NR3ZNY","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":"54167dc6885648d5e78a5736152affda988819c0b4b275a85015b01970460f9b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:13:23Z","title_canon_sha256":"71f0dd86417ff1418df82f88eb9317c25420aced9b8c4785e8ef334c68cc6f83"},"schema_version":"1.0","source":{"id":"1903.06282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.06282","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.06282v2","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06282","created_at":"2026-05-17T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"NEM5WZEBQADM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NEM5WZEBQADM3QQ4","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NEM5WZEB","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:7172911299548fd56a90e083c0edaa3e1680eddd9439b1ba155acdc3666c10f6","target":"graph","created_at":"2026-05-17T23:51:04Z","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":"We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics to train a robot directly from joint states, using traditional robotic tools. We use an state-of-the-art implementation of the Proximal Policy Optimization, Trust Region Policy Optimization and Actor-Critic Kronecker-Factored Trust Region algorithms to learn policies in four different Modular Articulated Robotic Arm (MARA) environments. We support this process using a framework that communicates with typical tools used in robotics, such as Gazebo and Robot Operating System 2 (ROS 2). We evaluate several algo","authors_text":"Alejandro Solano Rueda, Elias Barba Moral, Lander Usategui San Juan, Nestor Gonzalez Lopez, Risto Kojcev, V\\'ictor Mayoral Vilches, Yue Leire Erro Nuin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:13:23Z","title":"ROS2Learn: a reinforcement learning framework for ROS 2"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06282","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":"sha256:696de4d5bbd831259de39e4faa61f55479917972632e38440157330f429e9bca","target":"record","created_at":"2026-05-17T23:51:04Z","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":"54167dc6885648d5e78a5736152affda988819c0b4b275a85015b01970460f9b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:13:23Z","title_canon_sha256":"71f0dd86417ff1418df82f88eb9317c25420aced9b8c4785e8ef334c68cc6f83"},"schema_version":"1.0","source":{"id":"1903.06282","kind":"arxiv","version":2}},"canonical_sha256":"6919db64818006cdc21c4dcfa6c7796e2ec688bc1a3764c3c594f1d8248f4d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6919db64818006cdc21c4dcfa6c7796e2ec688bc1a3764c3c594f1d8248f4d33","first_computed_at":"2026-05-17T23:51:04.725222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:04.725222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pvz9lLOdiVC51eD2qjTD7DVYA61u5Zv2Ij8XRw/Ulichy/EpYV5486WYNU0MEq9GKWdOwitQjwkiQ8gj21u0BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:04.725806Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.06282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:696de4d5bbd831259de39e4faa61f55479917972632e38440157330f429e9bca","sha256:7172911299548fd56a90e083c0edaa3e1680eddd9439b1ba155acdc3666c10f6"],"state_sha256":"dff20fc4274365c5cea38f83586b40598248ad2781345d93aafc2243aa3fd037"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXhEuiO0jpwagvM1JJN19MGYtuz0/g23lyDwcH7pb7BTZtXwHAIzlDAIuvSxuyTexsWwNwi7IFm73efb91lyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T08:18:58.678901Z","bundle_sha256":"b418abb9f5e8a62bb031a3c6fcdcdca5f65a1c62fec5a395e1b82d8c1b2343d0"}}