Deep reinforcement learning has shown remarkable capabilities in visual tasks,but it does not have a good generalization ability in the context of interference signals in the input images;this approach is therefore ha...Deep reinforcement learning has shown remarkable capabilities in visual tasks,but it does not have a good generalization ability in the context of interference signals in the input images;this approach is therefore hard to be applied to trained agents in a new environment.To enable agents to distinguish between noise signals and important pixels in images,data augmentation techniques and the establishment of auxiliary networks are proven effective solutions.We introduce a novel algorithm,namely,saliency-extracted Q-value by augmentation(SEQA),which encourages the agent to explore unknown states more comprehensively and focus its attention on important information.Specifically,SEQA masks out interfering features and extracts salient features and then updates the mask decoder network with critic losses to encourage the agent to focus on important features and make correct decisions.We evaluate our algorithm on the DeepMind Control generalization benchmark(DMControl-GB),and the experimental results show that our algorithm greatly improves training efficiency and stability.Meanwhile,our algorithm is superior to state-of-the-art reinforcement learning methods in terms of sample efficiency and generalization in most DMControl-GB tasks.展开更多
基金Project supported by the Academic and Technical Leaders and Backup Candidates Program of Anhui Province,China(No.2019h211)the Natural Science Foundation of Anhui Province,China(No.2208085ME128)。
文摘Deep reinforcement learning has shown remarkable capabilities in visual tasks,but it does not have a good generalization ability in the context of interference signals in the input images;this approach is therefore hard to be applied to trained agents in a new environment.To enable agents to distinguish between noise signals and important pixels in images,data augmentation techniques and the establishment of auxiliary networks are proven effective solutions.We introduce a novel algorithm,namely,saliency-extracted Q-value by augmentation(SEQA),which encourages the agent to explore unknown states more comprehensively and focus its attention on important information.Specifically,SEQA masks out interfering features and extracts salient features and then updates the mask decoder network with critic losses to encourage the agent to focus on important features and make correct decisions.We evaluate our algorithm on the DeepMind Control generalization benchmark(DMControl-GB),and the experimental results show that our algorithm greatly improves training efficiency and stability.Meanwhile,our algorithm is superior to state-of-the-art reinforcement learning methods in terms of sample efficiency and generalization in most DMControl-GB tasks.
