rQdia: Regularizing Q-Value Distributions With Image Augmentation
rQdia regularizes Q-value distributions with augmented images in pixel-based deep reinforcement learning. With a simple auxiliary loss, that equalizes these distributions via MSE, rQdia boosts DrQ and SAC on 9/12 and 10/12 tasks respectively in the MuJoCo Continuous Control Suite from pixels, and Data-Efficient Rainbow on 18/26 Atari Arcade environments. Gains are measured in both sample efficiency and longer-term training. Moreover, the addition of rQdia finally propels model-free continuous control from pixels over the state encoding baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDeep Reinforcement LearningImage AugmentationMuJoCoSimilar Papers 제목 키워드 기반
Go Small and Similar: A Simple Output Decay Brings Better Performance
Regularization and data augmentation methods have been widely used and become increasingly indispensable in deep learning training. Researchers who devote themselves to this have considered various possibilities. But so …
Data AugmentationImage Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-tra…
AllAtari Games 100kContinuous ControlContrastive Learning+6Regularizing Neural Networks by Penalizing Confident Output Distributions
We systematically explore regularizing neural networks by penalizing low entropy output distributions. We show that penalizing low entropy output distributions, which has been shown to improve exploration in reinforcemen…
General Classificationimage-classificationImage ClassificationLanguage Modeling+7DisturbLabel: Regularizing CNN on the Loss Layer
During a long period of time we are combating over-fitting in the CNN training process with model regularization, including weight decay, model averaging, data augmentation, etc. In this paper, we present DisturbLabel, a…
Data AugmentationSoftEdge: Regularizing Graph Classification with Random Soft Edges
Augmented graphs play a vital role in regularizing Graph Neural Networks (GNNs), which leverage information exchange along edges in graphs, in the form of message passing, for learning. Due to their effectiveness, simple…
ClassificationData AugmentationGraph Classification