Related papers: Automatic Curriculum Learning With Over-repetition…
Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…
A safe and efficient decision-making system is crucial for autonomous vehicles. However, the complexity of driving environments limits the effectiveness of many rule-based and machine learning approaches. Reinforcement Learning (RL), with…
In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…
Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems. We propose a method for multi-domain dialogue policy learning---termed NDQN, and apply it to an…
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by learning directly from image input. A deep neural network is used as a function approximator and requires no specific state information.…
Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…
Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and 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…
Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs). This set contains some perturbed MDPs from a nominal MDP (N-MDP) that…
Large language models (LLMs) increasingly serve as educational tools, yet evaluating their teaching capabilities remains challenging due to the resource-intensive, context-dependent, and methodologically complex nature of teacher-student…
We propose a learning architecture that allows symbolic control and guidance in reinforcement learning with deep neural networks. We introduce SymDQN, a novel modular approach that augments the existing Dueling Deep Q-Networks (DuelDQN)…
Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to…
Challenging problems of deep reinforcement learning systems with regard to the application on real systems are their adaptivity to changing environments and their efficiency w.r.t. computational resources and data. In the application of…
With the development of experimental quantum technology, quantum control has attracted increasing attention due to the realization of controllable artificial quantum systems. However, because quantum-mechanical systems are often too…
Deep Reinforcement Learning (DRL) offers a powerful approach to training neural network control policies for stochastic queuing networks (SQN). However, traditional DRL methods rely on offline simulations or static datasets, limiting their…
The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose…
Q-learning methods represent a commonly used class of algorithms in reinforcement learning: they are generally efficient and simple, and can be combined readily with function approximators for deep reinforcement learning (RL). However, the…
Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…
Offline Reinforcement Learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods…