Related papers: Switch-based Active Deep Dyna-Q: Efficient Adaptiv…

Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world…

Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for…

We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017]. In ActiveQA, question answering is framed as a reinforcement learning task in which an agent sits…

Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the…

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning…

Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a…

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to…

Due to the complexity and volatility of the traffic environment, decision-making in autonomous driving is a significantly hard problem. In this project, we use a Deep Q-Network, along with rule-based constraints to make lane-changing…

Quality-Diversity (QD) algorithms are powerful exploration algorithms that allow robots to discover large repertoires of diverse and high-performing skills. However, QD algorithms are sample inefficient and require millions of evaluations.…

When dealing with deep neural network (DNN) applications on edge devices, continuously updating the model is important. Although updating a model with real incoming data is ideal, using all of them is not always feasible due to limits, such…

Cooperation emergence in multi-agent systems represents a fundamental statistical physics problem where microscopic learning rules drive macroscopic collective behavior transitions. We propose a Q-learning-based variant of adaptive rewiring…

World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expertise and effort required to identify and integrate them.…

Classroom dialogue plays a crucial role in fostering student engagement and deeper learning. However, analysing dialogue sequences has traditionally relied on either theoretical frameworks or empirical descriptions of practice, with limited…

To realize the full potential of quantum technologies, finding good strategies to control quantum information processing devices in real time becomes increasingly important. Usually these strategies require a precise understanding of the…

In human decision-making tasks, individuals learn through trials and prediction errors. When individuals learn the task, some are more influenced by good outcomes, while others weigh bad outcomes more heavily. Such confirmation bias can…

Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that…

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a…

Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment,…

Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a…

In industrial environments, an increasing amount of wireless devices are used, which utilize license-free bands. As a consequence of these mutual interferences of wireless systems might decrease the state of coexistence. Therefore, a…