相关论文: Latent-Predictive Empowerment: Measuring Empowerme…

Large language model (LLM)-driven agents are emerging as a powerful new paradigm for solving complex problems. Despite the empirical success of these practices, a theoretical framework to understand and unify their macroscopic dynamics…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Prompt Engineering (PE) has emerged as a critical technique for guiding Large Language Models (LLMs) in solving intricate tasks. Its importance is highlighted by its potential to significantly enhance the efficiency and effectiveness of…

How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the…

Learning by examples, which learns to solve a new problem by looking into how similar problems are solved, is an effective learning method in human learning. When a student learns a new topic, he/she finds out exemplar topics that are…

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for…

How can artificial agents learn to solve many diverse tasks in complex visual environments in the absence of any supervision? We decompose this question into two problems: discovering new goals and learning to reliably achieve them. We…

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…

Reinforcement learning (RL) is a promising approach for robotic manipulation, but it can suffer from low sample efficiency and requires extensive exploration of large state-action spaces. Recent methods leverage the commonsense knowledge…

The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task…

Joint Embedding Predictive Architectures (JEPA) offer a scalable paradigm for self-supervised learning by predicting latent representations rather than reconstructing high-entropy observations. However, existing formulations rely on…

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate…

Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans,…

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…

Reinforcement learning agents have been mostly developed and evaluated under the assumption that they will operate in a fully autonomous manner -- they will take all actions. In this work, our goal is to develop algorithms that, by learning…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively…

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner…

The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of…