{"id":"2606.10580","title":"Convergence of Monte Carlo Optimistic Policy Iteration: Beyond Uniform State-Action Updates","url":"https://codeofpaper.com/paper/2606.10580","arxiv_url":"https://arxiv.org/abs/2606.10580","published":"2026-06-09","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}