Related papers: The Impact of Task Underspecification in Evaluatin…
Many existing traffic signal controllers are either simple adaptive controllers based on sensors placed around traffic intersections, or optimized by traffic engineers on a fixed schedule. Optimizing traffic controllers is time consuming…
Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains…
While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments of RAS pose new challenges on its…
Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially…
Urban Traffic Control (UTC) plays an essential role in Intelligent Transportation System (ITS) but remains difficult. Since model-based UTC methods may not accurately describe the complex nature of traffic dynamics in all situations,…
Researchers have demonstrated that Deep Reinforcement Learning (DRL) is a powerful tool for finding policies that perform well on complex robotic systems. However, these policies are often unpredictable and can induce highly variable…
Multi-robot navigation and path planning in continuous state and action spaces with uncertain environments remains an open challenge. Deep Reinforcement Learning (RL) is one of the most popular paradigms for solving this task, but its…
One key challenge for multi-task Reinforcement learning (RL) in practice is the absence of task indicators. Robust RL has been applied to deal with task ambiguity, but may result in over-conservative policies. To balance the worst-case…
Exploiting unmanned aerial vehicles (UAVs) to execute tasks is gaining growing popularity recently. To solve the underlying task scheduling problem, the deep reinforcement learning (DRL) based methods demonstrate notable advantage over the…
Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making tasks across diverse domains, yet its reliance on black-box neural architectures hinders interpretability, trust, and deployment in high-stakes…
We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms…
While researchers in the asset management industry have mostly focused on techniques based on financial and risk planning techniques like Markowitz efficient frontier, minimum variance, maximum diversification or equal risk parity, in…
Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…
Autonomous mobile robots are increasingly used in pedestrian-rich environments where safe navigation and appropriate human interaction are crucial. While Deep Reinforcement Learning (DRL) enables socially integrated robot behavior,…
Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for…
Reinforcement Learning (RL) has demonstrated strong potential for industrial process control, yet policies trained in simulation often suffer from a significant sim-to-real gap when deployed on physical hardware. This work systematically…
Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose…
With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable…
The risks and perils of overfitting in machine learning are well known. However most of the treatment of this, including diagnostic tools and remedies, was developed for the supervised learning case. In this work, we aim to offer new…
Contextual Reinforcement Learning (CRL) tackles the problem of solving a set of related Contextual Markov Decision Processes (CMDPs) that vary across different context variables. Traditional approaches--independent training and multi-task…