Uncertainty-Guided Active Reinforcement Learning with Bayesian Neural Networks
Xinyang Wu,Mohamed El-Shamouty,Christof Nitsche,Marco F. Huber,Xinyang Wu,Mohamed El-Shamouty,Christof Nitsche,Marco F. Huber
Recent advances in Reinforcement Learning (RL) have made significant contributions in past years by offering intelligent solutions to solve robotic tasks. However, most RL algorithms, especially the model-free RL, are plagued by low learning efficiency and safety problems. In this paper, we propose using the Bayesian Neural Networks (BNNs) to guide the agent exploring actively to enhance the learn...
