Search Results for author:
Found 67 papers, 25 papers with code
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy.
Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation
Existing off-policy reinforcement learning algorithms typically necessitate an explicit state-action-value function representation, which becomes problematic in high-dimensional action spaces.
Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
This work introduces PI-MGNs, a hybrid approach that combines PINNs and MGNs to quickly and accurately solve non-stationary and nonlinear partial differential equations (PDEs) on arbitrary meshes.
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Current advancements in reinforcement learning (RL) have predominantly focused on learning step-based policies that generate actions for each perceived state.
Neural Contractive Dynamical Systems
Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions.
Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming
Industrial robots are applied in a widening range of industries, but robot programming mostly remains a task limited to programming experts.
Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects
Policy learning in robot-assisted surgery (RAS) lacks data efficient and versatile methods that exhibit the desired motion quality for delicate surgical interventions.
Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud
In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object.
Latent Task-Specific Graph Network Simulators
Movement primitives further allow us to accommodate various types of context data, as demonstrated through the utilization of point clouds during inference.
Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization
Before each update, it solves the trust region problem for an optimal step size, resulting in a more stable and faster optimization process.
Multi Time Scale World Models
Intelligent agents use internal world models to reason and make predictions about different courses of their actions at many scales.
SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects
To enable meaningful robotic manipulation of objects in the real-world, 6D pose estimation is one of the critical aspects.
Enhancing Interpretable Object Abstraction via Clustering-based Slot Initialization
In our work, we initialize the slot representations with clustering algorithms conditioned on the perceptual input features.
DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes
The results demonstrate the effectiveness of the proposed approach in predicting versatile and dense grasps, and in advancing the field of multi-fingered robotic grasping.
SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation
Detecting objects and estimating their 6D poses is essential for automated systems to interact safely with the environment.
MP3: Movement Primitive-Based (Re-)Planning Policy
We introduce a novel deep reinforcement learning (RL) approach called Movement Primitive-based Planning Policy (MP3).
Curriculum-Based Imitation of Versatile Skills
Learning skills by imitation is a promising concept for the intuitive teaching of robots.
Swarm Reinforcement Learning For Adaptive Mesh Refinement
Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enabling a favorable trade-off between computational speed and simulation accuracy.
Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills
Imitation learning uses data for training policies to solve complex tasks.
Grounding Graph Network Simulators using Physical Sensor Observations
Our method results in utilization of additional point cloud information to accurately predict stable simulations where existing Graph Network Simulators fail.
Joint Representations for Reinforcement Learning with Multiple Sensors
Combining inputs from multiple sensor modalities effectively in reinforcement learning (RL) is an open problem.
Deep Black-Box Reinforcement Learning with Movement Primitives
In this paper, we present a new algorithm for deep ERL.
Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors
We find that the geometric descriptors greatly help in generalizing to new task configurations and that combining them with our distribution-matching objective is crucial for representing and reproducing versatile behavior.
On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning
We show that RSSMs use a suboptimal inference scheme and that models trained using this inference overestimate the aleatoric uncertainty of the ground truth system.
Model-based Reinforcement Learning
reinforcement-learning
+2
ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives
MPs can be broadly categorized into two types: (a) dynamics-based approaches that generate smooth trajectories from any initial state, e. g., Dynamic Movement Primitives (DMPs), and (b) probabilistic approaches that capture higher-order statistics of the motion, e. g., Probabilistic Movement Primitives (ProMPs).
A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models
The two currently most effective methods for GMM-based variational inference, VIPS and iBayes-GMM, both employ independent natural gradient updates for the individual components and their weights.
FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion
Sensor fusion can significantly improve the performance of many computer vision tasks.
MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network
We overcome this issue with our novel multi-view 6D pose estimation method called MV6D which accurately predicts the 6D poses of all objects in a cluttered scene based on RGB-D images from multiple perspectives.
Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination
Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found.
Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system identification.
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes
We present a novel meta-learning approach for 6D pose estimation on unknown objects.
End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control
These models need to precisely capture the robot dynamics, which consist of well-understood components, e. g., rigid body dynamics, and effects that remain challenging to capture, e. g., stick-slip friction and mechanical flexibilities.
Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control
In contrast, stochastic optimizers that are motivated by policy gradients, such as the Model-based Relative Entropy Stochastic Search (MORE) algorithm, directly optimize the expected fitness function without the use of rankings.
Meta-Learning Regrasping Strategies for Physical-Agnostic Objects
Grasping inhomogeneous objects in real-world applications remains a challenging task due to the unknown physical properties such as mass distribution and coefficient of friction.
Reactive Motion Generation on Learned Riemannian Manifolds
We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills.
What Matters For Meta-Learning Vision Regression Tasks?
To this end, we (i) exhaustively evaluate common meta-learning techniques on these tasks, and (ii) quantitatively analyze the effect of various deep learning techniques commonly used in recent meta-learning algorithms in order to strengthen the generalization capability: data augmentation, domain randomization, task augmentation and meta-regularization.
Specializing Versatile Skill Libraries using Local Mixture of Experts
This local and incremental learning results in a modular MoE model of high accuracy and versatility, where both properties can be scaled by adding more components on the fly.
Switching Recurrent Kalman Networks
In addition, driving data can often be multimodal in distribution, meaning that there are distinct predictions that are likely, but averaging can hurt model performance.
Versatile Inverse Reinforcement Learning via Cumulative Rewards
Inverse Reinforcement Learning infers a reward function from expert demonstrations, aiming to encode the behavior and intentions of the expert.
A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models
Effective approaches for Gaussian variational inference are MORE, VOGN, and VON, which are zero-order, first-order, and second-order, respectively.
A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning
We argue that it is crucial to automate the reward learning process so that new skills can be taught to robots by their users.
Differentiable Robust LQR Layers
This paper proposes a differentiable robust LQR layer for reinforcement learning and imitation learning under model uncertainty and stochastic dynamics.
Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty
We propose a new formulation that addresses these limitations by also modifying the feedback signals to the controller with an RL policy and show superior performance of our approach on a contact-rich peg-insertion task under position and orientation uncertainty.
Learning Riemannian Manifolds for Geodesic Motion Skills
For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly.
Differentiable Trust Region Layers for Deep Reinforcement Learning
However, enforcing such trust regions in deep reinforcement learning is difficult.
Bayesian Context Aggregation for Neural Processes
Recently, casting probabilistic regression as a multi-task learning problem in terms of conditional latent variable (CLV) models such as the Neural Process (NP) has shown promising results.
Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning
We adopt a recent probabilistic recurrent neural network architecture, called Re-current Kalman Networks (RKNs), to model learning by conditioning its transition dynamics on the control actions.
Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space
Since actual hardware implementation of microgravity environment is extremely expensive, the demonstration data for trajectory learning is generated using a model predictive controller (MPC) in a physics based simulator.
Non-Adversarial Imitation Learning and its Connections to Adversarial Methods
We also show that our non-adversarial formulation can be used to derive novel algorithms by presenting a method for offline imitation learning that is inspired by the recent ValueDice algorithm, but does not rely on small policy updates for convergence.
Expected Information Maximization: Using the I-Projection for Mixture Density Estimation
Such behavior is appealing whenever we deal with highly multi-modal data where modelling single modes correctly is more important than covering all the modes.
Trust-Region Variational Inference with Gaussian Mixture Models
For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently.
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference techniques such as variational inference which makes learning more complex and often less scalable due to approximation errors.
Compatible Natural Gradient Policy Search
Trust-region methods have yielded state-of-the-art results in policy search.
An Algorithmic Perspective on Imitation Learning
This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning.
Adaptation and Robust Learning of Probabilistic Movement Primitives
However, to be able to capture variability and correlations between different joints, a probabilistic movement primitive requires the estimation of a larger number of parameters compared to their deterministic counterparts, that focus on modeling only the mean behavior.
Towards Fine Grained Network Flow Prediction
In this space, into which we transform the input data via a Short-Time Fourier Transform (STFT), the peak structures of flows can be predicted after gleaning their key characteristics, with a Principal Component Analysis (PCA), from past and ongoing flows that stem from the same socket-to-socket connection.
Deep Reinforcement Learning for Swarm Systems
However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant.
Efficient Gradient-Free Variational Inference using Policy Search
Inference from complex distributions is a common problem in machine learning needed for many Bayesian methods.
Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning
Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents.
Guided Deep Reinforcement Learning for Swarm Systems
Here, we follow a guided approach where a critic has central access to the global state during learning, which simplifies the policy evaluation problem from a reinforcement learning point of view.
Local Bayesian Optimization of Motor Skills
Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization.
Catching heuristics are optimal control policies
In this paper, we show that interception strategies appearing to be heuristics can be understood as computational solutions to the optimal control problem faced by a ball-catching agent acting under uncertainty.
Policy Search with High-Dimensional Context Variables
A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored.
Model-Free Trajectory-based Policy Optimization with Monotonic Improvement
In order to show the monotonic improvement of our algorithm, we additionally conduct a theoretical analysis of our policy update scheme to derive a lower bound of the change in policy return between successive iterations.
Model-Based Relative Entropy Stochastic Search
Stochastic search algorithms are general black-box optimizers.
Probabilistic Movement Primitives
In order to use such a trajectory distribution for robot movement control, we analytically derive a stochastic feedback controller which reproduces the given trajectory distribution.
Fitted Q-iteration by Advantage Weighted Regression
Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the resulting policy.
