{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Y74C2YAEZQ7DE5AFCLR4SRSAQL","short_pith_number":"pith:Y74C2YAE","schema_version":"1.0","canonical_sha256":"c7f82d6004cc3e32740512e3c9464082f598e1e8ebbae1fee05561bbcd2d53de","source":{"kind":"arxiv","id":"1903.06278","version":2},"attestation_state":"computed","paper":{"title":"gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo","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":"2019-03-14T22:05:20Z","abstract_excerpt":"This paper presents an upgraded, real world application oriented version of gym-gazebo, the Robot Operating System (ROS) and Gazebo based Reinforcement Learning (RL) toolkit, which complies with OpenAI Gym. The content discusses the new ROS 2 based software architecture and summarizes the results obtained using Proximal Policy Optimization (PPO). Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and algorithms to be compared using the same virtual conditions. We have evaluated environments with different levels of complexity of the"},"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":"1903.06278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-14T22:05:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"86e504e19f3749beacd18bea8db54e8d93938bcf8fa7b77f368c8697f7bdcbb2","abstract_canon_sha256":"9462b55eebca90b1ce3cd1f188a304ec53fb5978080ece19995d073ea5fbdf5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:04.732051Z","signature_b64":"Z+a3FY7p57OQ1wmvxbl9MdK26RbhK7CHsBIPcGXjCBWuGp1VWgpxbjhX+CCJRlgQiVAb3CB8LKsYGmr0X+BQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7f82d6004cc3e32740512e3c9464082f598e1e8ebbae1fee05561bbcd2d53de","last_reissued_at":"2026-05-17T23:51:04.731647Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:04.731647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo","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":"2019-03-14T22:05:20Z","abstract_excerpt":"This paper presents an upgraded, real world application oriented version of gym-gazebo, the Robot Operating System (ROS) and Gazebo based Reinforcement Learning (RL) toolkit, which complies with OpenAI Gym. The content discusses the new ROS 2 based software architecture and summarizes the results obtained using Proximal Policy Optimization (PPO). Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and algorithms to be compared using the same virtual conditions. We have evaluated environments with different levels of complexity of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06278","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.06278","created_at":"2026-05-17T23:51:04.731705+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.06278v2","created_at":"2026-05-17T23:51:04.731705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06278","created_at":"2026-05-17T23:51:04.731705+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y74C2YAEZQ7D","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y74C2YAEZQ7DE5AF","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y74C2YAE","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.05407","citing_title":"RouteFormer: A Transformer-Based Routing Framework for Autonomous Vehicles","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04225","citing_title":"ARMATA: Auto-Regressive Multi-Agent Task Assignment","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL","json":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL.json","graph_json":"https://pith.science/api/pith-number/Y74C2YAEZQ7DE5AFCLR4SRSAQL/graph.json","events_json":"https://pith.science/api/pith-number/Y74C2YAEZQ7DE5AFCLR4SRSAQL/events.json","paper":"https://pith.science/paper/Y74C2YAE"},"agent_actions":{"view_html":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL","download_json":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL.json","view_paper":"https://pith.science/paper/Y74C2YAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.06278&json=true","fetch_graph":"https://pith.science/api/pith-number/Y74C2YAEZQ7DE5AFCLR4SRSAQL/graph.json","fetch_events":"https://pith.science/api/pith-number/Y74C2YAEZQ7DE5AFCLR4SRSAQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL/action/storage_attestation","attest_author":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL/action/author_attestation","sign_citation":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL/action/citation_signature","submit_replication":"https://pith.science/pith/Y74C2YAEZQ7DE5AFCLR4SRSAQL/action/replication_record"}},"created_at":"2026-05-17T23:51:04.731705+00:00","updated_at":"2026-05-17T23:51:04.731705+00:00"}