Related papers: Modular Recurrence in Contextual MDPs for Universa…

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple…

We propose a shared semantic map architecture to construct and configure Model Predictive Controllers (MPC) dynamically, that solve navigation problems for multiple robotic agents sharing parts of the same environment. The navigation task…

Decision-making agents with planning capabilities have achieved huge success in the challenging domain like Chess, Shogi, and Go. In an effort to generalize the planning ability to the more general tasks where the environment dynamics are…

We present a general approach for controlling robotic systems that make and break contact with their environments. Contact-implicit model predictive control (CI-MPC) generalizes linear MPC to contact-rich settings by utilizing a bi-level…

Novel imaging and neurostimulation techniques open doors for advancements in closed-loop control of activity in biological neural networks. This would allow for applications in the investigation of activity propagation, and for diagnosis…

Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently. We improve on previous environment simulators from high-dimensional pixel observations by introducing recurrent…

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…

Humans and animals developed a sophisticated motor control apparatus and there is much evidence that it has a modular structure. The modularity offers a range of benefits, e.g. ability to learn dissociable motion styles without interference…

We present controllers that enable mobile robots to persistently monitor or sweep a changing environment. The changing environment is modeled as a field which grows in locations that are not within range of a robot, and decreases in…

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics…

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of…

Multi-Objective Learning Model Predictive Control is a novel data-driven control scheme which improves a linear system's closed-loop performance with respect to several convex control objectives over iterations of a repeated task. At each…

The co-design of robot morphology and neural control typically requires using reinforcement learning to approximate a unique control policy gradient for each body plan, demanding massive amounts of training data to measure the performance…

Given a dataset of expert trajectories, standard imitation learning approaches typically learn a direct mapping from observations (e.g., RGB images) to actions. However, such methods often overlook the rich interplay between different…

Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations…

Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…

The main question this paper addresses is: What combination of a robot controller and a learning method should be used, if the morphology of the learning robot is not known in advance? Our interest is rooted in the context of…

Sociability is essential for modern robots to increase their acceptability in human environments. Traditional techniques use manually engineered utility functions inspired by observing pedestrian behaviors to achieve social navigation.…

Multi-robot systems can greatly enhance efficiency through coordination and collaboration, yet in practice, full-time communication is rarely available and interactions are constrained to close-range exchanges. Existing methods either…