{"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/a-simple-randomization-technique-for-1","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","arxiv_id":"1910.05396","date":"2019-10-11","proceeding":"ICLR 2020 1","authors":["Kimin Lee","Kibok Lee","Jinwoo Shin","Honglak Lee"],"abstract":"Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we propose a simple technique to improve a generalization ability of deep RL agents by introducing a randomized (convolutional) neural network that randomly perturbs input observations. It enables trained agents to adapt to new domains by learning robust features invariant across varied and randomized environments. Furthermore, we consider an inference method based on the Monte Carlo approximation to reduce the variance induced by this randomization. We demonstrate the superiority of our method across 2D CoinRun, 3D DeepMind Lab exploration and 3D robotics control tasks: it significantly outperforms various regularization and data augmentation methods for the same purpose.","url_abs":"https://arxiv.org/abs/1910.05396v3","url_pdf":"https://arxiv.org/pdf/1910.05396v3.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":"a-simple-randomization-technique-for-1","repo_url":"https://github.com/pokaxpoka/netrand","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-randomization-technique-for-1","repo_url":"https://github.com/ankurhanda/rand_conv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-randomization-technique-for-1","repo_url":"https://github.com/1hb6s7t/Rand-conv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"a-simple-randomization-technique-for-1","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"a-simple-randomization-technique-for-1","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/7/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"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":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.05396","atlas_url":"https://app.syntology.ai/?focus=1910.05396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05396"}},"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/pwc-1/Paper-9/tree/main/7/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ankurhanda/rand_conv","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pokaxpoka/netrand","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/4/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1hb6s7t/Rand-conv","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"8758308dc6c0727f","entry":"constfn","repo":"pokaxpoka/netrand","repo_kind":"official","path":"sources/ppo2.py","file_url":"https://github.com/pokaxpoka/netrand/blob/HEAD/sources/ppo2.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8758308dc6c0727f"}},{"code_sha256_prefix":"baf2a28d376d7803","entry":"sf01","repo":"pokaxpoka/netrand","repo_kind":"official","path":"sources/ppo2.py","file_url":"https://github.com/pokaxpoka/netrand/blob/HEAD/sources/ppo2.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baf2a28d376d7803"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}