{"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/policy-teaching-via-environment-poisoning","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","arxiv_id":"2003.12909","date":"2020-03-28","proceeding":"ICML 2020 1","authors":["Amin Rakhsha","Goran Radanovic","Rati Devidze","Xiaojin Zhu","Adish Singla"],"abstract":"We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \\emph{optimal stealthy attack} for different measures of attack cost. We provide sufficient technical conditions under which the attack is feasible and provide lower/upper bounds on the attack cost. We instantiate our attacks in two settings: (i) an \\emph{offline} setting where the agent is doing planning in the poisoned environment, and (ii) an \\emph{online} setting where the agent is learning a policy using a regret-minimization framework with poisoned feedback. Our results show that the attacker can easily succeed in teaching any target policy to the victim under mild conditions and highlight a significant security threat to reinforcement learning agents in practice.","url_abs":"https://arxiv.org/abs/2003.12909v2","url_pdf":"https://arxiv.org/pdf/2003.12909v2.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":"policy-teaching-via-environment-poisoning","repo_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.12909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.12909"}},"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/adishs/icml2020_rl-policy-teaching_code","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"c0b20e0ab6155170","entry":"accumulator_function","repo":"adishs/icml2020_rl-policy-teaching_code","repo_kind":"official","path":"teaching_offline_vary_c.py","file_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code/blob/HEAD/teaching_offline_vary_c.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0b20e0ab6155170"}},{"code_sha256_prefix":"5ddb7a19339e6e8c","entry":"calculate_average","repo":"adishs/icml2020_rl-policy-teaching_code","repo_kind":"official","path":"teaching_online.py","file_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code/blob/HEAD/teaching_online.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ddb7a19339e6e8c"}},{"code_sha256_prefix":"1e7e0dab32de8029","entry":"get_M","repo":"adishs/icml2020_rl-policy-teaching_code","repo_kind":"official","path":"teaching_offline_vary_c.py","file_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code/blob/HEAD/teaching_offline_vary_c.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e7e0dab32de8029"}},{"code_sha256_prefix":"eaeaa3440f96715e","entry":"dynamic_attack_nontargetonly","repo":"adishs/icml2020_rl-policy-teaching_code","repo_kind":"official","path":"code-attacker/dynamic_attack.py","file_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code/blob/HEAD/code-attacker/dynamic_attack.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":"eaeaa3440f96715e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}