{"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/crossnorm-normalization-for-off-policy-td","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","arxiv_id":"1902.05605","date":"2019-02-14","proceeding":null,"authors":["Aditya Bhatt","Daniel Palenicek","Boris Belousov","Max Argus","Artemij Amiranashvili","Thomas Brox","Jan Peters"],"abstract":"Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while maintaining a low UTD ratio of 1. Notably, CrossQ does not rely on advanced bias-reduction schemes used in current methods. CrossQ's contributions are threefold: (1) it matches or surpasses current state-of-the-art methods in terms of sample efficiency, (2) it substantially reduces the computational cost compared to REDQ and DroQ, (3) it is easy to implement, requiring just a few lines of code on top of SAC.","url_abs":"https://arxiv.org/abs/1902.05605v4","url_pdf":"https://arxiv.org/pdf/1902.05605v4.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":"crossnorm-normalization-for-off-policy-td","repo_url":"https://github.com/adityab/crossq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"crossnorm-normalization-for-off-policy-td","repo_url":"https://github.com/markub3327/rl-toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"crossnorm-normalization-for-off-policy-td","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"crossnorm-normalization-for-off-policy-td","repo_url":"https://github.com/Ipsedo/EvoMotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"crossnorm-normalization-for-off-policy-td","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"clipped-double-q-learning","method_name":"Clipped Double Q-learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"ddpg","method_name":"DDPG"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.05605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}