Related papers: Interactive Differentiable Simulation
Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…
Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…
Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to low training efficiency and poor generalization. To address…
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are sample efficient, and interpretable but often rely on rigid assumptions. Furthermore, direct numerical approximation…
Simulation modeling of robots, objects, and environments is the backbone for all model-based control and learning. It is leveraged broadly across dynamic programming and model-predictive control, as well as data generation for imitation,…
Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to obtain sensorimotor…
The identification of a mathematical dynamics model is a crucial step in the designing process of a controller. However, it is often very difficult to identify the system's governing equations, especially in complex environments that…
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which…
Active inference is a mathematical framework for understanding how agents (biological or artificial) interact with their environments, enabling continual adaptation and decision-making. It combines Bayesian inference and free energy…
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning…
We present a differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects within a unified framework. Through a principled mollification of normal and tangential contact forces, our method…
Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the…
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…
Combining model-based and model-free learning systems has been shown to improve the sample efficiency of learning to perform complex robotic tasks. However, dual-system approaches fail to consider the reliability of the learned model when…
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to…
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…
Model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments. Moreover, in the presence of variations in the operating conditions, the model should…
Assessing the systemic effects of uncertainty that arises from agents' partial observation of the true states of the world is critical for understanding a wide range of scenarios. Yet, previous modeling work on agent learning and…
Inverse Distance Weighted models (IDW) have been widely used for predicting and modeling multidimensional space in multimodal industrial processes. However, the more complex the structure of multidimensional space, the lower the performance…
We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the…