Related papers: Modular Recurrence in Contextual MDPs for Universa…

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challenging multi-task reinforcement learning problem, as the…

Multiple domains like vision, natural language, and audio are witnessing tremendous progress by leveraging Transformers for large scale pre-training followed by task specific fine tuning. In contrast, in robotics we primarily train a single…

In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are…

A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual…

The theoretical ability of modular robots to reconfigure in response to complex tasks in a priori unknown environments has frequently been cited as an advantage and remains a major motivator for work in the field. We present a modular robot…

Control of complex systems involves both system identification and controller design. Deep neural networks have proven to be successful in many identification tasks, however, from model-based control perspective, these networks are…

Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised framework for learning hierarchical manipulation concepts…

Adapting to the changes in transition dynamics is essential in robotic applications. By learning a conditional policy with a compact context, context-aware meta-reinforcement learning provides a flexible way to adjust behavior according to…

Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings. However, real-world robotics systems often present challenges that limit…

There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned surrogate models that describe dynamics and rewards of…

Learning from real-world robot demonstrations holds promise for interacting with complex real-world environments. However, the complexity and variability of interaction dynamics often cause purely positional controllers to struggle with…

Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach…

To perform manipulation tasks in the real world, robots need to operate on objects with various shapes, sizes and without access to geometric models. It is often unfeasible to train monolithic neural network policies across such large…

Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a…

Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network…

Multi-degree-of-freedom (DOF) robotic manipulators exhibit strongly nonlinear, high-dimensional, and coupled dynamics, posing significant challenges for controller design. To address these issues, this work proposes a unified hybrid control…

Modern, torque-controlled service robots can regulate contact forces when interacting with their environment. Model Predictive Control (MPC) is a powerful method to solve the underlying control problem, allowing to plan for whole-body…

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

Learning has propelled the cutting edge of performance in robotic control to new heights, allowing robots to operate with high performance in conditions that were previously unimaginable. The majority of the work, however, assumes that the…

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific…