{"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/cleanba-a-reproducible-and-efficient","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","arxiv_id":"2310.00036","date":"2023-09-29","proceeding":null,"authors":["Shengyi Huang","Jiayi Weng","Rujikorn Charakorn","Min Lin","Zhongwen Xu","Santiago Ontañón"],"abstract":"Distributed Deep Reinforcement Learning (DRL) aims to leverage more computational resources to train autonomous agents with less training time. Despite recent progress in the field, reproducibility issues have not been sufficiently explored. This paper first shows that the typical actor-learner framework can have reproducibility issues even if hyperparameters are controlled. We then introduce Cleanba, a new open-source platform for distributed DRL that proposes a highly reproducible architecture. Cleanba implements highly optimized distributed variants of PPO and IMPALA. Our Atari experiments show that these variants can obtain equivalent or higher scores than strong IMPALA baselines in moolib and torchbeast and PPO baseline in CleanRL. However, Cleanba variants present 1) shorter training time and 2) more reproducible learning curves in different hardware settings. Cleanba's source code is available at \\url{https://github.com/vwxyzjn/cleanba}","url_abs":"https://arxiv.org/abs/2310.00036v1","url_pdf":"https://arxiv.org/pdf/2310.00036v1.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":"cleanba-a-reproducible-and-efficient","repo_url":"https://github.com/vwxyzjn/cleanba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"impala","method_name":"IMPALA"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"torchbeast","method_name":"TorchBeast"},{"method_slug":"v-trace","method_name":"V-trace"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.00036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00036"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/vwxyzjn/cleanba","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":8,"samples":[{"code_sha256_prefix":"e48c3f5e91815524","entry":"prepare_data","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e48c3f5e91815524"}},{"code_sha256_prefix":"0a8d9a0bb82d5cba","entry":"prepare_data","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_actor_threads.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_actor_threads.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0a8d9a0bb82d5cba"}},{"code_sha256_prefix":"473a0670886aa8a5","entry":"scale_by_rms_pytorch_style","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/cleanba_impala.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/cleanba_impala.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"473a0670886aa8a5"}},{"code_sha256_prefix":"a4e7c034e397476d","entry":"scale_by_rms_pytorch_style","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_rmsprop_pt.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_rmsprop_pt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a4e7c034e397476d"}},{"code_sha256_prefix":"01a6c2cfba0e3978","entry":"get_action","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"01a6c2cfba0e3978"}},{"code_sha256_prefix":"a7cfe9ab0009183d","entry":"get_action","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_last_action_reward.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_machado_atari_wrapper_last_action_reward.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a7cfe9ab0009183d"}},{"code_sha256_prefix":"f3bb7f4cb552e938","entry":"get_action_and_value","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper_last_action_reward.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper_last_action_reward.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f3bb7f4cb552e938"}},{"code_sha256_prefix":"f9afbfc516e71798","entry":"prepare_data","repo":"vwxyzjn/cleanba","repo_kind":"official","path":"cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper_last_action_reward.py","file_url":"https://github.com/vwxyzjn/cleanba/blob/HEAD/cleanba/legacy_scripts/cleanba_impala_envpool_impala_atari_wrapper_last_action_reward.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f9afbfc516e71798"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}