{"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/efficient-risk-averse-reinforcement-learning","title":"Efficient Risk-Averse Reinforcement Learning","arxiv_id":"2205.05138","date":"2022-05-10","proceeding":null,"authors":["Ido Greenberg","Yinlam Chow","Mohammad Ghavamzadeh","Shie Mannor"],"abstract":"In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. A risk measure often focuses on the worst returns out of the agent's experience. As a result, standard methods for risk-averse RL often ignore high-return strategies. We prove that under certain conditions this inevitably leads to a local-optimum barrier, and propose a soft risk mechanism to bypass it. We also devise a novel Cross Entropy module for risk sampling, which (1) preserves risk aversion despite the soft risk; (2) independently improves sample efficiency. By separating the risk aversion of the sampler and the optimizer, we can sample episodes with poor conditions, yet optimize with respect to successful strategies. We combine these two concepts in CeSoR - Cross-entropy Soft-Risk optimization algorithm - which can be applied on top of any risk-averse policy gradient (PG) method. We demonstrate improved risk aversion in maze navigation, autonomous driving, and resource allocation benchmarks, including in scenarios where standard risk-averse PG completely fails.","url_abs":"https://arxiv.org/abs/2205.05138v2","url_pdf":"https://arxiv.org/pdf/2205.05138v2.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":"efficient-risk-averse-reinforcement-learning","repo_url":"https://github.com/ido90/CeSoR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"efficient-risk-averse-reinforcement-learning","repo_url":"https://github.com/fictivename/cesor_ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"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=2205.05138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05138"}},"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/ido90/CeSoR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fictivename/cesor_ppo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_fixture":1,"unverified":11},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":10,"ran":0,"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":"86e963f7b7e3adbd","entry":"alpha_scheduler","repo":"ido90/CeSoR","repo_kind":"official","path":"GCVaR.py","file_url":"https://github.com/ido90/CeSoR/blob/HEAD/GCVaR.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86e963f7b7e3adbd"}},{"code_sha256_prefix":"39c3d160a2608b68","entry":"quantile","repo":"ido90/CeSoR","repo_kind":"official","path":"GCVaR.py","file_url":"https://github.com/ido90/CeSoR/blob/HEAD/GCVaR.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39c3d160a2608b68"}},{"code_sha256_prefix":"afa5dec3b7dd3040","entry":"GCVaR","repo":"ido90/CeSoR","repo_kind":"official","path":"GCVaR.py","file_url":"https://github.com/ido90/CeSoR/blob/HEAD/GCVaR.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":"afa5dec3b7dd3040"}},{"code_sha256_prefix":"ecc112d81d06387e","entry":"boolean_argument","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"config/args_khazad_dum_varibad.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/config/args_khazad_dum_varibad.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":"ecc112d81d06387e"}},{"code_sha256_prefix":"2059f84e6efc564f","entry":"create_mlp","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/stable_baselines3/common/torch_layers.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":"2059f84e6efc564f"}},{"code_sha256_prefix":"13e8fba090dd2ac4","entry":"cyan","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"launch_sweep.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/launch_sweep.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":"13e8fba090dd2ac4"}},{"code_sha256_prefix":"80fc122d961f23c2","entry":"env_step","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/utils/helpers.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":"80fc122d961f23c2"}},{"code_sha256_prefix":"f2ded9c22d608f44","entry":"get_actor_critic_arch","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"stable_baselines3/common/torch_layers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/stable_baselines3/common/torch_layers.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":"f2ded9c22d608f44"}},{"code_sha256_prefix":"85e29bef821e4c23","entry":"get_args","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"config/args_khazad_dum_varibad.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/config/args_khazad_dum_varibad.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":"85e29bef821e4c23"}},{"code_sha256_prefix":"fcfceb90cb8b29ef","entry":"mujoco_wrapper","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"environments/wrappers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/environments/wrappers.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":"fcfceb90cb8b29ef"}},{"code_sha256_prefix":"09c0cd83d9a903cb","entry":"reset_env","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/utils/helpers.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":"09c0cd83d9a903cb"}},{"code_sha256_prefix":"c9ed03000a43a992","entry":"squash_action","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/utils/helpers.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":"c9ed03000a43a992"}},{"code_sha256_prefix":"aa0a3b5212b8b5ad","entry":"yellow","repo":"fictivename/cesor_ppo","repo_kind":"listed","path":"launch_sweep.py","file_url":"https://github.com/fictivename/cesor_ppo/blob/HEAD/launch_sweep.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":"aa0a3b5212b8b5ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}