{"id":"2409.08938","title":"Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks","url":"https://codeofpaper.com/paper/2409.08938","arxiv_url":"https://arxiv.org/abs/2409.08938","published":"2024-09-13","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}