Related papers: TCRL: Temporal-Coupled Adversarial Training for Ro…
Contrastive Reinforcement Learning (CRL) provides a promising framework for extracting useful structured representations from unlabeled interactions. By pulling together state-action pairs and their corresponding future states, while…
Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity…
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations…
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…
We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined…
Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…
Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…
Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article presents a novel deep reinforcement learning (DRL) controller…
Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks. In this paper, we are specifically…
In the classical Reinforcement Learning (RL) setting, one aims to find a policy that maximizes its expected return. This objective may be inappropriate in safety-critical domains such as healthcare or autonomous driving, where intrinsic…
Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted to training environments, RL methods have often failed to be…
In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…
Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…
Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its…
We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some…
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of…
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…
We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…
Reinforcement learning (RL) depends critically on the choice of reward functions used to capture the de- sired behavior and constraints of a robot. Usually, these are handcrafted by a expert designer and represent heuristics for relatively…
In this paper, we study a novel episodic risk-sensitive Reinforcement Learning (RL) problem, named Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each step, and focuses on tightly controlling the risk of getting…