{"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/probabilistic-perspectives-on-error","title":"Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning","arxiv_id":"2406.04724","date":"2024-06-07","proceeding":null,"authors":["Roman Belaire","Arunesh Sinha","Pradeep Varakantham"],"abstract":"Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. For instance, a self-driving car could experience catastrophic consequences if its sensory inputs about traffic signs are manipulated by an adversary. The core challenge in such situations is that the true state of the environment becomes only partially observable due to these adversarial manipulations. Two key strategies have so far been employed in the literature; the first set of methods focuses on increasing the likelihood that nearby states--those close to the true state--share the same robust actions. The second set of approaches maximize the value for the worst possible true state within the range of adversarially perturbed observations. Although these approaches provide strong robustness against attacks, they tend to be either overly conservative or not generalizable. We hypothesize that the shortcomings of these approaches stem from their failure to explicitly account for partial observability. By making decisions that directly consider this partial knowledge of the true state, we believe it is possible to achieve a better balance between robustness and performance, particularly in adversarial settings. To achieve this, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), which is defined on the beliefs about the underlying true state and naturally balances value optimization with robustness against adversarial attacks, and a theoretically-grounded, scalable surrogate objective Cumulative-ACoE (C-ACoE). Our empirical evaluations demonstrate that our method significantly outperforms current state-of-the-art approaches for addressing adversarial RL challenges, offering a promising direction for better DRL under adversarial conditions.","url_abs":"https://arxiv.org/abs/2406.04724v2","url_pdf":"https://arxiv.org/pdf/2406.04724v2.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":"probabilistic-perspectives-on-error","repo_url":"https://github.com/romanbelaire/acoe-robust-rl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.04724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04724"}},"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":"deterministic:regex_extraction","url":"https://github.com/umd-huang-lab/WocaR-RL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/romanbelaire/acoe-robust-rl","reach":null}],"summary":{"ran":6,"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"found_in_text":{"samples":10,"ran":7,"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":"69017b3a991e0815","entry":"activation_bound","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/SA-DQN/models.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/SA-DQN/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69017b3a991e0815"}},{"code_sha256_prefix":"35b6f17122388f57","entry":"dict_product","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-PPO/src/utils.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-PPO/src/utils.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":"35b6f17122388f57"}},{"code_sha256_prefix":"85bf3d86b586cab7","entry":"get_alg_name","repo":"romanbelaire/acoe-robust-rl","repo_kind":"official","path":"get_best_pickle.py","file_url":"https://github.com/romanbelaire/acoe-robust-rl/blob/HEAD/get_best_pickle.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85bf3d86b586cab7"}},{"code_sha256_prefix":"aa0592ec6641ad10","entry":"get_alg_name","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-PPO/src/get_best_pickle.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-PPO/src/get_best_pickle.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa0592ec6641ad10"}},{"code_sha256_prefix":"35a892ade6c313d2","entry":"get_env_name","repo":"romanbelaire/acoe-robust-rl","repo_kind":"official","path":"get_best_pickle.py","file_url":"https://github.com/romanbelaire/acoe-robust-rl/blob/HEAD/get_best_pickle.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35a892ade6c313d2"}},{"code_sha256_prefix":"cfb1c3dd218b92f0","entry":"initial_bounds","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/RA-DQN/ibp.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/RA-DQN/ibp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cfb1c3dd218b92f0"}},{"code_sha256_prefix":"942706632c22fc44","entry":"iwt","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-PPO/src/utils.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-PPO/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"942706632c22fc44"}},{"code_sha256_prefix":"23ff92a17dc4fd23","entry":"process_frame","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/RA-DQN/environment.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/RA-DQN/environment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23ff92a17dc4fd23"}},{"code_sha256_prefix":"eba320329ae9cb63","entry":"weighted_bound","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/SA-DQN/models.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/SA-DQN/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eba320329ae9cb63"}},{"code_sha256_prefix":"09c7359e9f493f7c","entry":"atari_env","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/RA-DQN/environment.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/RA-DQN/environment.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09c7359e9f493f7c"}},{"code_sha256_prefix":"4000c95fa330f2ce","entry":"read_config","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/RA-DQN/utils.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/RA-DQN/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4000c95fa330f2ce"}},{"code_sha256_prefix":"3a204c610b328628","entry":"record_game","repo":"umd-huang-lab/WocaR-RL","repo_kind":"found_in_text","path":"WocaR-DQN/RA-DQN/evaluate.py","file_url":"https://github.com/umd-huang-lab/WocaR-RL/blob/HEAD/WocaR-DQN/RA-DQN/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a204c610b328628"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}