相关论文: EUCLID: Towards Efficient Unsupervised Reinforceme…

Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learning, diffusion maps, or more recently self-supervised…

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy…

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the…

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…

Many state-of-the-art reinforcement learning (RL) algorithms typically assume that the environment is an ergodic Markov Decision Process (MDP). In contrast, the field of universal reinforcement learning (URL) is concerned with algorithms…

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience,…

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

Model-based reinforcement learning (MBRL) has demonstrated superior sample efficiency compared to model-free reinforcement learning (MFRL). However, the presence of inaccurate models can introduce biases during policy learning, resulting in…

This paper considers a class of reinforcement learning problems, which involve systems with two types of states: stochastic and pseudo-stochastic. In such systems, stochastic states follow a stochastic transition kernel while the…

Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…

Reinforcement learning (RL) has been a promising essence in future 5G-beyond and 6G systems. Its main advantage lies in its robust model-free decision-making in complex and large-dimension wireless environments. However, most existing RL…

Representation learning has significantly driven the field to develop pretrained models that can act as a valuable starting point when transferring to new datasets. With the rising demand for reliable machine learning and uncertainty…

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing learning value as training progresses. Existing dynamic…

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error,…

We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally-efficient,…

This paper addresses the problem of learning optimal control policies for systems with uncertain dynamics and high-level control objectives specified as Linear Temporal Logic (LTL) formulas. Uncertainty is considered in the workspace…

Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts well to unseen tasks, multiple meta-training approaches have…