Related papers: Model-Based Reinforcement Learning via Latent-Spac…

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically…

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL)…

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic…

Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned…

While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue,…

We propose a new class of deep reinforcement learning (RL) algorithms that model latent representations in hyperbolic space. Sequential decision-making requires reasoning about the possible future consequences of current behavior.…

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert…

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one…

A cognitive beamforming algorithm for colocated MIMO radars, based on Reinforcement Learning (RL) framework, is proposed. We analyse an RL-based optimization protocol that allows the MIMO radar, i.e. the \textit{agent}, to iteratively sense…

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…

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a single model end-to-end for learning both visual…

An emergency responder management (ERM) system dispatches responders, such as ambulances, when it receives requests for medical aid. ERM systems can also proactively reposition responders between predesignated waiting locations to cover any…

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…