Related papers: Unsupervised Zero-Shot Reinforcement Learning via …

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed…

Reinforcement Learning (RL) agents have demonstrated their potential across various robotic tasks. However, they still heavily rely on human-engineered reward functions, requiring extensive trial-and-error and access to target behavior…

Current neural decoding methods typically aim at explaining behavior based on neural activity via supervised learning. However, since generally there is a strong connection between learning of subjects and their expectations on long-term…

Using learned reward functions (LRFs) as a means to solve sparse-reward reinforcement learning (RL) tasks has yielded some steady progress in task-complexity through the years. In this work, we question whether today's LRFs are best-suited…

Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might…

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through…

Functional MRI measuring BOLD signal is an increasingly important imaging modality in studying brain functions and neurological disorders. It can be acquired in either a resting-state or a task-based paradigm. Compared to resting-state…

We study zero-shot generalization in reinforcement learning-optimizing a policy on a set of training tasks to perform well on a similar but unseen test task. To mitigate overfitting, previous work explored different notions of invariance to…

The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective…

Reinforcement learning (RL) often struggles in real-world tasks with high-dimensional state spaces and long horizons, where sparse or fixed rewards severely slow down exploration and cause agents to get trapped in local optima. This paper…

While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or…

Offline reinforcement learning (RL) can learn control policies from static datasets but, like standard RL methods, it requires reward annotations for every transition. In many cases, labeling large datasets with rewards may be costly,…

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments.…

In reinforcement learning, we typically refer to unsupervised pre-training when we aim to pre-train a policy without a priori access to the task specification, i.e. rewards, to be later employed for efficient learning of downstream tasks.…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques.…

Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing…