Related papers: DROID: Minimizing the Reality Gap using Single-Sho…

Several applications in the scientific simulation of physical systems can be formulated as control/optimization problems. The computational models for such systems generally contain hyperparameters, which control solution fidelity and…

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…

Dynamic real-time optimization (DRTO) is a challenging task due to the fact that optimal operating conditions must be computed in real time. The main bottleneck in the industrial application of DRTO is the presence of uncertainty. Many…

In robotics, gradient-free optimization algorithms (e.g. evolutionary algorithms) are often used only in simulation because they require the evaluation of many candidate solutions. Nevertheless, solutions obtained in simulation often do not…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simulation, and then…

Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with…

Reinforcement learning has enjoyed multiple successes in recent years. However, these successes typically require very large amounts of data before an agent achieves acceptable performance. This paper introduces a novel way of combating…

With the ability to learn from static datasets, Offline Reinforcement Learning (RL) emerges as a compelling avenue for real-world applications. However, state-of-the-art offline RL algorithms perform sub-optimally when confronted with…

Despite recent advances in reinforcement learning (RL), its application in safety critical domains like autonomous vehicles is still challenging. Although punishing RL agents for risky situations can help to learn safe policies, it may also…

Domain randomisation is a very popular method for visual sim-to-real transfer in robotics, due to its simplicity and ability to achieve transfer without any real-world images at all. Nonetheless, a number of design choices must be made to…

We propose a novel iterative approach for crossing the reality gap that utilises live robot rollouts and differentiable physics. Our method, RealityGrad, demonstrates for the first time, an efficient sim2real transfer in combination with a…

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Robot foundation models are beginning to deliver on the promise of generalist robotic agents, yet progress remains constrained by the scarcity of large-scale real-world manipulation datasets. Simulation and synthetic data generation offer a…

Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust…

Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed loop, leading to compounding errors. We introduce Rollouts…

In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…

Learning-based approaches, particularly reinforcement learning (RL), have become widely used for developing control policies for autonomous agents, such as locomotion policies for legged robots. RL training typically maximizes a predefined…

A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training. In this paper, we approach this challenge through the following invariance principle: an agent…

Humans generally teach their fellow collaborators to perform tasks through a small number of demonstrations. The learnt task is corrected or extended to meet specific task goals by means of coaching. Adopting a similar framework for…