Related papers: RIDM: Reinforced Inverse Dynamics Modeling for Lea…

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

Achieving stable and robust perceptive locomotion for bipedal robots in unstructured outdoor environments remains a critical challenge due to complex terrain geometry and susceptibility to external disturbances. In this work, we propose a…

Autonomous off-road driving is challenging as risky actions taken by the robot may lead to catastrophic damage. As such, developing controllers in simulation is often desirable as it provides a safer and more economical alternative.…

Although reinforcement learning methods offer a powerful framework for automatic skill acquisition, for practical learning-based control problems in domains such as robotics, imitation learning often provides a more convenient and…

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations.…

Inverse Reinforcement Learning (IRL) is the task of learning a single reward function given a Markov Decision Process (MDP) without defining the reward function, and a set of demonstrations generated by humans/experts. However, in practice,…

In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known.…

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…

Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from…

Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…

Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observation spaces prevalent in robotics. This paper addresses the…

Inverse dynamics is used extensively in robotics and biomechanics applications. In manipulator and legged robots, it can form the basis of an effective nonlinear control strategy by providing a robot with both accurate positional tracking…

Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach…

Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous…

Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult. However, despite the success of IL algorithms, they impose the somewhat unrealistic requirement that…

In recent years, reinforcement learning (RL) has shown outstanding performance for locomotion control of highly articulated robotic systems. Such approaches typically involve tedious reward function tuning to achieve the desired motion…

Precise robotic manipulation skills are desirable in many industrial settings, reinforcement learning (RL) methods hold the promise of acquiring these skills autonomously. In this paper, we explicitly consider incorporating operational…

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the…

In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can…

Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs…