Related papers: OPEn: An Open-ended Physics Environment for Learni…

Building machines capable of efficiently collaborating with humans has been a longstanding goal in artificial intelligence. Especially in the presence of uncertainties, optimal cooperation often requires that humans and artificial agents…

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…

Most work on physical reasoning, both in artificial intelligence and in cognitive science, has focused on closed-world reasoning, in which it is assumed that the problem specification specifies all relevant objects and substance, all their…

Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, the reward function…

Training intelligent agents that can drive autonomously in various urban and highway scenarios has been a hot topic in the robotics society within the last decades. However, the diversity of driving environments in terms of road topology…

Autonomous agents are increasingly expected to operate in complex, dynamic, and uncertain environments, performing tasks such as manipulation, navigation, and decision-making. Achieving these capabilities requires agents to understand the…

Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years. One of the key challenges in manipulation is the exploration of the dynamics of the environment when…

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Teaching robots to learn diverse locomotion skills under complex three-dimensional environmental settings via Reinforcement Learning (RL) is still challenging. It has been shown that training agents in simple settings before moving them on…

Visual navigation by mobile robots is classically tackled through SLAM plus optimal planning, and more recently through end-to-end training of policies implemented as deep networks. While the former are often limited to waypoint planning,…

In the last decade, the free energy principle (FEP) and active inference (AIF) have achieved many successes connecting conceptual models of learning and cognition to mathematical models of perception and action. This effort is driven by a…

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or…

Artificial Intelligence methods to solve continuous- control tasks have made significant progress in recent years. However, these algorithms have important limitations and still need significant improvement to be used in industry and real-…

Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to…

If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown…

Agents that are aware of the separation between themselves and their environments can leverage this understanding to form effective representations of visual input. We propose an approach for learning such structured representations for RL…

Space exploration missions have seen use of increasingly sophisticated robotic systems with ever more autonomy. Deep learning promises to take this even a step further, and has applications for high-level tasks, like path planning, as well…

Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. We present a…

Robots should exist anywhere humans do: indoors, outdoors, and even unmapped environments. In contrast, the focus of recent advancements in Object Goal Navigation(OGN) has targeted navigating in indoor environments by leveraging spatial and…

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…