{"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/breaking-the-barrier-enhanced-utility-and","title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents","arxiv_id":"2406.18062","date":"2024-06-26","proceeding":null,"authors":["Chung-En Sun","Sicun Gao","Tsui-Wei Weng"],"abstract":"Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee across standard RL benchmarks. Notably, our S-DQN and S-PPO agents not only significantly outperform existing smoothed agents by an average factor of $2.16\\times$ under the strongest attack, but also surpass previous robustly-trained agents by an average factor of $2.13\\times$. This represents a significant leap forward in the field. Furthermore, we introduce Smoothed Attack, which is $1.89\\times$ more effective in decreasing the rewards of smoothed agents than existing adversarial attacks.","url_abs":"https://arxiv.org/abs/2406.18062v1","url_pdf":"https://arxiv.org/pdf/2406.18062v1.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":"breaking-the-barrier-enhanced-utility-and","repo_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"}],"methods":[{"method_slug":"randomized-smoothing","method_name":"Randomized Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.18062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18062"}},"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/trustworthy-ml-lab/robust_highutil_smoothed_drl","reach":null}],"summary":{"ran_violates":1,"ran_honours":5,"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"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":12,"samples":[{"code_sha256_prefix":"e74f5b2a28ba8052","entry":"action_scheduler","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/train_denoiser.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/train_denoiser.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e74f5b2a28ba8052"}},{"code_sha256_prefix":"7700197c7cc5747d","entry":"arctanh_rescale","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7700197c7cc5747d"}},{"code_sha256_prefix":"85a898709da49405","entry":"fgsm","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"85a898709da49405"}},{"code_sha256_prefix":"5a2c00df265799e5","entry":"pgd","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a2c00df265799e5"}},{"code_sha256_prefix":"e271cea23daebf1a","entry":"rand_attack","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e271cea23daebf1a"}},{"code_sha256_prefix":"6919817644c97093","entry":"sigma_scheduler","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/train_denoiser.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/train_denoiser.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6919817644c97093"}},{"code_sha256_prefix":"9eeb6bd6911481c2","entry":"tanh_rescale","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9eeb6bd6911481c2"}},{"code_sha256_prefix":"488e5c100aa0a20b","entry":"to_one_hot","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"488e5c100aa0a20b"}},{"code_sha256_prefix":"6a1ba12807275000","entry":"torch_arctanh","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a1ba12807275000"}},{"code_sha256_prefix":"bf58e2c221ef74b2","entry":"attack","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.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":"bf58e2c221ef74b2"}},{"code_sha256_prefix":"681b6da6079555d4","entry":"compute_td_loss","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/train_denoiser.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/train_denoiser.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":"681b6da6079555d4"}},{"code_sha256_prefix":"f43cc787cc6c05de","entry":"cw","repo":"trustworthy-ml-lab/robust_highutil_smoothed_drl","repo_kind":"official","path":"SDQN/attacks.py","file_url":"https://github.com/trustworthy-ml-lab/robust_highutil_smoothed_drl/blob/HEAD/SDQN/attacks.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":"f43cc787cc6c05de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}