Language Assistance in Reinforcement Learning in Dynamic Environments

Language is an intuitive and effective way for humans to communicate. Large Language Models (LLMs) can interpret and respond well to language. However, their use in deep reinforcement learning is limited as they are sample inefficient. State-of-the-art deep reinforcement learning algorithms are more sample efficient but cannot understand...

Activity Progress Prediction: Is there progress in video progress prediction methods?

In this paper, we investigate the behaviour of current progress prediction methods on the currently used benchmark datasets. We show that the progress prediction methods can fail to extract useful information from visual data on these datasets. Moreover, when the methods fail to extract visual information, memory-based methods adopt a frame...

Prioritizing states with action sensitive return in experience replay

Experience replay for off-policy reinforcement learning has been shown to improve sample efficiency and stabilize training. However, typical uniformly sampled replay includes many irrelevant samples for the agent to reach good performance. We introduce Action Sensitive Experience Replay (ASER), a method to prioritize samples in the replay buffer...

Multi-objective Deep Reinforcement Learning for predictive maintenance of road networks

Operation and maintenance of the built environment have a major effect on socioeconomic stability and sustainability. A significant part of our built world approaches or has well exceeded its designated structural life. As engineers, we need to find efficient ways to extend this life while maintaining acceptable levels of safety and performance....

Vanishing empirical variance in randomly initialized networks

Neural networks are commonly initialized to keep the theoretical variance of the hidden pre-activations constant, in order to avoid the vanishing and exploding gradient problem. Though this condition is necessary to train very deep networks, numerous analyses showed that it is not sufficient. We explain this fact by analyzing the behavior of the...

Learning to search & track dynamic targets with graph representations

Autonomous robots have been widely applied to search and rescue missions for information gathering about target locations. This process needs to be continuously replanned based on new observations in the environment. For dynamic targets, the robot needs to not only discover them but also keep tracking their positions. Previous works focus on...