相关论文: Reinforcement Learning from Imperfect Demonstratio…

This paper proposes a robust control design method using reinforcement-learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement-learning algorithm with a new…

Reinforcement learning provides a powerful and general framework for decision making and control, but its application in practice is often hindered by the need for extensive feature and reward engineering. Deep reinforcement learning…

Designing a stabilizing controller for nonlinear systems is a challenging task, especially for high-dimensional problems with unknown dynamics. Traditional reinforcement learning algorithms applied to stabilization tasks tend to drive the…

Although in recent years reinforcement learning has become very popular the number of successful applications to different kinds of operations research problems is rather scarce. Reinforcement learning is based on the well-studied dynamic…

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic…

Modular robots can be reconfigured to create a variety of designs from a small set of components. But constructing a robot's hardware on its own is not enough -- each robot needs a controller. One could create controllers for some designs…

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of…

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a…

Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To…

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk…

Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found. Traditional methods used in this area are imitation learning and reinforcement learning, but they both have…

We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which start with learning from demonstrations (LfD) and then use…

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…