{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sample-factory-egocentric-3d-control-from","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","arxiv_id":"2006.11751","date":"2020-06-21","proceeding":"ICML 2020 1","authors":["Aleksei Petrenko","Zhehui Huang","Tushar Kumar","Gaurav Sukhatme","Vladlen Koltun"],"abstract":"Increasing the scale of reinforcement learning experiments has allowed researchers to achieve unprecedented results in both training sophisticated agents for video games, and in sim-to-real transfer for robotics. Typically such experiments rely on large distributed systems and require expensive hardware setups, limiting wider access to this exciting area of research. In this work we aim to solve this problem by optimizing the efficiency and resource utilization of reinforcement learning algorithms instead of relying on distributed computation. We present the \"Sample Factory\", a high-throughput training system optimized for a single-machine setting. Our architecture combines a highly efficient, asynchronous, GPU-based sampler with off-policy correction techniques, allowing us to achieve throughput higher than $10^5$ environment frames/second on non-trivial control problems in 3D without sacrificing sample efficiency. We extend Sample Factory to support self-play and population-based training and apply these techniques to train highly capable agents for a multiplayer first-person shooter game. The source code is available at https://github.com/alex-petrenko/sample-factory","url_abs":"https://arxiv.org/abs/2006.11751v2","url_pdf":"https://arxiv.org/pdf/2006.11751v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sample-factory-egocentric-3d-control-from","repo_url":"https://github.com/alex-petrenko/sample-factory","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sample-factory-egocentric-3d-control-from","repo_url":"https://github.com/ngoodger/nle-language-wrapper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sample-factory-egocentric-3d-control-from","repo_url":"https://github.com/pervasive-ai-lab/nle-language-wrapper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sample-factory-egocentric-3d-control-from","repo_url":"https://github.com/opendilab/DI-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fps-games","task_name":"FPS Games"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"general-reinforcement-learning","task_name":"General Reinforcement Learning"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"appo","method_name":"APPO"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[{"slug":"appo","name":"APPO","full_name":"Asynchronous Proximal Policy Optimization"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.11751","atlas_url":"https://app.syntology.ai/?focus=2006.11751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11751"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alex-petrenko/sample-factory","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ngoodger/nle-language-wrapper","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pervasive-ai-lab/nle-language-wrapper","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7fb8a5bac84c8654","entry":"fc_layer","repo":"alex-petrenko/sample-factory","repo_kind":"official","path":"sample_factory/model/model_utils.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/model/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7fb8a5bac84c8654"}},{"code_sha256_prefix":"fdc600b61ce97ca2","entry":"generate_args","repo":"alex-petrenko/sample-factory","repo_kind":"official","path":"sample_factory/export_onnx.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/export_onnx.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc600b61ce97ca2"}},{"code_sha256_prefix":"03ab87432391e2ee","entry":"get_rnn_size","repo":"alex-petrenko/sample-factory","repo_kind":"official","path":"sample_factory/model/model_utils.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/model/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03ab87432391e2ee"}},{"code_sha256_prefix":"d24d8d4729dd54c7","entry":"he_normal_init","repo":"alex-petrenko/sample-factory","repo_kind":"official","path":"sample_factory/model/utils.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d24d8d4729dd54c7"}},{"code_sha256_prefix":"ec56f732ad5319e0","entry":"orthogonal_init","repo":"alex-petrenko/sample-factory","repo_kind":"official","path":"sample_factory/model/utils.py","file_url":"https://github.com/alex-petrenko/sample-factory/blob/HEAD/sample_factory/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec56f732ad5319e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}