{"url":"/method/kova","slug":"kova","name":"KOVA","full_name":"Kalman Optimization for Value Approximation","full_name_withheld":false,"description_markdown":"**Kalman Optimization for Value Approximation**, or **KOVA** is a general framework for addressing uncertainties while approximating value-based functions in deep RL domains. KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties. It is feasible when using non-linear approximation functions as DNNs and can estimate the value in both on-policy and off-policy settings. It can be incorporated as a policy evaluation component in policy optimization algorithms.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Kalman meets Bellman: Improving Policy Evaluation through Value Tracking","paper":"/paper/kalman-meets-bellman-improving-policy","first_author":"Shirli Di-Castro Shashua","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/kalman-meets-bellman-improving-policy"},"source":{"url":"https://arxiv.org/abs/2002.07171v1","title":"Kalman meets Bellman: Improving Policy Evaluation through Value Tracking","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Policy Evaluation","url":"/methods/category/policy-evaluation","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/kalman-meets-bellman-improving-policy","title":"Kalman meets Bellman: Improving Policy Evaluation through Value Tracking","date":"2020-02-17","arxiv_id":"2002.07171","n_code_links":1,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/gaussian-processes","name":"Gaussian Processes","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/kova"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}