相关论文: Switching Successor Measures for Hierarchical Zero…

Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the given task into…

Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single high-level embedding, using it as fixed guidance…

Learning policies which are robust to changes in the environment are critical for real world deployment of Reinforcement Learning agents. They are also necessary for achieving good generalization across environment shifts. We focus on…

Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of…

Generalizing to long-horizon manipulation tasks in a zero-shot setting remains a central challenge in robotics. Current multimodal foundation based approaches, despite their capabilities, typically fail to decompose high-level commands into…

Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing approaches suffer from several limitations: they may require…

Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing, and transferring predictive knowledge and behavior. SF&GPI works by having an agent learn…

In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set…

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores…

The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks,…

Efficiently aggregating spatial or temporal horizons to acquire compact representations has become a unifying principle in modern deep learning models, yet learning data-adaptive representations for long-horizon sequence data, especially…

Recent work has shown that, under certain assumptions, zero-shot reinforcement learning (RL) methods can generalise to any unseen task in an environment after reward-free pre-training. Access to Markov states is one such assumption, yet, in…

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses…

Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can learn from few-shot examples to generate a classifier.…

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change…

In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal represen tation function, abstracting state space into…

Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function…

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…