{"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/normalization-enhances-generalization-in","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","arxiv_id":"2306.00656","date":"2023-06-01","proceeding":null,"authors":["Lu Li","Jiafei Lyu","Guozheng Ma","Zilin Wang","Zhenjie Yang","Xiu Li","Zhiheng Li"],"abstract":"Recent advances in visual reinforcement learning (RL) have led to impressive success in handling complex tasks. However, these methods have demonstrated limited generalization capability to visual disturbances, which poses a significant challenge for their real-world application and adaptability. Though normalization techniques have demonstrated huge success in supervised and unsupervised learning, their applications in visual RL are still scarce. In this paper, we explore the potential benefits of integrating normalization into visual RL methods with respect to generalization performance. We find that, perhaps surprisingly, incorporating suitable normalization techniques is sufficient to enhance the generalization capabilities, without any additional special design. We utilize the combination of two normalization techniques, CrossNorm and SelfNorm, for generalizable visual RL. Extensive experiments are conducted on DMControl Generalization Benchmark and CARLA to validate the effectiveness of our method. We show that our method significantly improves generalization capability while only marginally affecting sample efficiency. In particular, when integrated with DrQ-v2, our method enhances the test performance of DrQ-v2 on CARLA across various scenarios, from 14% of the training performance to 97%.","url_abs":"https://arxiv.org/abs/2306.00656v1","url_pdf":"https://arxiv.org/pdf/2306.00656v1.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":"normalization-enhances-generalization-in","repo_url":"https://github.com/lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.00656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00656"}},"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/lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning","reach":null}],"summary":{"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"bc0eace99a0f0cc7","entry":"calc_ins_mean_std","repo":"lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning","repo_kind":"official","path":"cnsn_dmcgb/src/algorithms/cnsn.py","file_url":"https://github.com/lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning/blob/HEAD/cnsn_dmcgb/src/algorithms/cnsn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc0eace99a0f0cc7"}},{"code_sha256_prefix":"32ae32759f281900","entry":"instance_norm_mix","repo":"lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning","repo_kind":"official","path":"cnsn_dmcgb/src/algorithms/cnsn.py","file_url":"https://github.com/lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning/blob/HEAD/cnsn_dmcgb/src/algorithms/cnsn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32ae32759f281900"}},{"code_sha256_prefix":"5e329c5ce37d7b65","entry":"cn_rand_bbox","repo":"lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning","repo_kind":"official","path":"cnsn_dmcgb/src/algorithms/cnsn.py","file_url":"https://github.com/lilucse/Normalization-Enhances-Generalization-in-Visual-Reinforcement-Learning/blob/HEAD/cnsn_dmcgb/src/algorithms/cnsn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e329c5ce37d7b65"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}