{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HYCLM5GHNJWBTAMFMW3LWYT3PE","short_pith_number":"pith:HYCLM5GH","schema_version":"1.0","canonical_sha256":"3e04b674c76a6c19818565b6bb627b792d72db4ab10f3c1c55c54fef94f14531","source":{"kind":"arxiv","id":"1809.02627","version":2},"attestation_state":"computed","paper":{"title":"Unity: A General Platform for Intelligent Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Cohen, Arthur Juliani, Chris Elion, Chris Goy, Danny Lange, Ervin Teng, Hunter Henry, Jonathan Harper, Marwan Mattar, Vincent-Pierre Berges, Yuan Gao","submitted_at":"2018-09-07T18:13:25Z","abstract_excerpt":"Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for interaction among artificial agents. Furthermore, many platforms lack the ability to flexibly configure the simulation, making the simulated environment a black-box from the perspective of the learning system. In this work, we propose a novel taxonomy of existing simulation platforms a"},"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":"1809.02627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T18:13:25Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"a5f02a543bc025e7fb7771d2fb9494936630fc570483b1f1732f8ec93a2244a1","abstract_canon_sha256":"7c54834a51c7ba7203fc5b77ff4e7c853c77a5bb3ab95c20e491628a5ba99b4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:45.979634Z","signature_b64":"32c6WUp7+rSmzszUlBDx/4P+k8Gv9im+j6oyLSYS8hu7zhJQP8Z9It7Qpr14Tif+NdHuYeSJxpbb9SgLoKQcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e04b674c76a6c19818565b6bb627b792d72db4ab10f3c1c55c54fef94f14531","last_reissued_at":"2026-07-05T01:00:45.979197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:45.979197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unity: A General Platform for Intelligent Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Cohen, Arthur Juliani, Chris Elion, Chris Goy, Danny Lange, Ervin Teng, Hunter Henry, Jonathan Harper, Marwan Mattar, Vincent-Pierre Berges, Yuan Gao","submitted_at":"2018-09-07T18:13:25Z","abstract_excerpt":"Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for interaction among artificial agents. Furthermore, many platforms lack the ability to flexibly configure the simulation, making the simulated environment a black-box from the perspective of the learning system. In this work, we propose a novel taxonomy of existing simulation platforms a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02627","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/1809.02627/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.02627","created_at":"2026-07-05T01:00:45.979263+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02627v2","created_at":"2026-07-05T01:00:45.979263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02627","created_at":"2026-07-05T01:00:45.979263+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYCLM5GHNJWB","created_at":"2026-07-05T01:00:45.979263+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYCLM5GHNJWBTAMF","created_at":"2026-07-05T01:00:45.979263+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYCLM5GH","created_at":"2026-07-05T01:00:45.979263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06514","citing_title":"FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18786","citing_title":"R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09236","citing_title":"Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03551","citing_title":"NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for Robotics","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02832","citing_title":"An Exploration of Collision-based Enemy Morphology Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"1906.11633","citing_title":"ORRB -- OpenAI Remote Rendering Backend","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08052","citing_title":"An Introduction to Deep Reinforcement and Imitation Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19503","citing_title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19503","citing_title":"ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27162","citing_title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08713","citing_title":"REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10263","citing_title":"Infernux: A Python-Native Game Engine with JIT-Accelerated Scripting","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE","json":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE.json","graph_json":"https://pith.science/api/pith-number/HYCLM5GHNJWBTAMFMW3LWYT3PE/graph.json","events_json":"https://pith.science/api/pith-number/HYCLM5GHNJWBTAMFMW3LWYT3PE/events.json","paper":"https://pith.science/paper/HYCLM5GH"},"agent_actions":{"view_html":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE","download_json":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE.json","view_paper":"https://pith.science/paper/HYCLM5GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02627&json=true","fetch_graph":"https://pith.science/api/pith-number/HYCLM5GHNJWBTAMFMW3LWYT3PE/graph.json","fetch_events":"https://pith.science/api/pith-number/HYCLM5GHNJWBTAMFMW3LWYT3PE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE/action/storage_attestation","attest_author":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE/action/author_attestation","sign_citation":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE/action/citation_signature","submit_replication":"https://pith.science/pith/HYCLM5GHNJWBTAMFMW3LWYT3PE/action/replication_record"}},"created_at":"2026-07-05T01:00:45.979263+00:00","updated_at":"2026-07-05T01:00:45.979263+00:00"}