Search Results for author:
Found 19 papers, 4 papers with code
Accelerating Model-Based Reinforcement Learning with State-Space World Models
However, training a world model alongside the policy increases the computational complexity, leading to longer training times that are often intractable for complex real-world scenarios.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
Multi-Task Reinforcement Learning for Quadrotors
Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios.
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories.
Student-Informed Teacher Training
In this framework, a teacher is trained with privileged task information, while a student tries to predict the actions of the teacher with more limited observations, e. g., in a robot navigation task, the teacher might have access to distances to nearby obstacles, while the student only receives visual observations of the scene.
LIMT: Language-Informed Multi-Task Visual World Models
Our results highlight the benefits of using language-driven task representations for world models and a clear advantage of model-based multi-task learning over the more common model-free paradigm.
The Shortcomings of Force-from-Motion in Robot Learning
Robotic manipulation requires accurate motion and physical interaction control.
Guided Decoding for Robot On-line Motion Generation and Adaption
We present a novel motion generation approach for robot arms, with high degrees of freedom, in complex settings that can adapt online to obstacles or new via points.
On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
We study the choice of action space in robot manipulation learning and sim-to-real transfer.
CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts.
Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space
We combine these components through a bio-inspired action space that we call AFORCE.
Dual-Arm Adversarial Robot Learning
This is due to the additional challenges encountered in the real-world, such as noisy sensors and actuators, safe exploration, non-stationary dynamics, autonomous environment resetting as well as the cost of running experiments for long periods of time.
Learning to Centralize Dual-Arm Assembly
Hence, to avoid modeling the interaction between the two robots and the used assembly tools, we present a modular approach with two decentralized single-arm controllers which are coupled using a single centralized learned policy.
Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning
Our method enhances the exploration capability of RL algorithms, by taking advantage of the SRL setup.
Making Curiosity Explicit in Vision-based RL
Our method enhances the exploration capability of the RL algorithms by taking advantage of the SRL setup.
Learning Vision-based Reactive Policies for Obstacle Avoidance
In this paper, we address the problem of vision-based obstacle avoidance for robotic manipulators.
How to Make Deep RL Work in Practice
Additionally, techniques from supervised learning are often used by default but influence the algorithms in a reinforcement learning setting in different and not well-understood ways.
Task-Independent Spiking Central Pattern Generator: A Learning-Based Approach
This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuroscience.
Tracking Holistic Object Representations
The framework leverages the idea of obtaining additional object templates during the tracking process.
Ranked #3 on
Visual Object Tracking
on VOT2017/18
Clustering with Deep Learning: Taxonomy and New Methods
In this paper, we propose a systematic taxonomy of clustering methods that utilize deep neural networks.
