{"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/sunrise-a-simple-unified-framework-for","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","arxiv_id":"2007.04938","date":"2020-07-09","proceeding":null,"authors":["Kimin Lee","Michael Laskin","Aravind Srinivas","Pieter Abbeel"],"abstract":"Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments. Our training code is available at https://github.com/pokaxpoka/sunrise.","url_abs":"https://arxiv.org/abs/2007.04938v4","url_pdf":"https://arxiv.org/pdf/2007.04938v4.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":"sunrise-a-simple-unified-framework-for","repo_url":"https://github.com/pokaxpoka/sunrise","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"dueling-network","method_name":"Dueling Network"},{"method_slug":"n-step-returns","method_name":"N-step Returns"},{"method_slug":"noisy-net","method_name":"Noisy Linear Layer"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"rainbow-dqn","method_name":"Rainbow DQN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.04938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}