相关论文: On the role of planning in model-based deep reinfo…

We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change the properties of the resultant models. By testing this…

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve…

We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent. We find that on an environment that requires multimodal posterior…

In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method. We investigate the practical utility of two…

Reinforcement Learning (RL) has shown remarkable progress in simulation environments, yet its application to real-world robotic tasks remains limited due to challenges in exploration and generalization. To address these issues, we introduce…

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…

An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When…

There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches. In this paper we attempt to evaluate this intuition on various challenging locomotion tasks. We take a…

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for…

Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…

Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…

Humans learn to play video games significantly faster than the state-of-the-art reinforcement learning (RL) algorithms. People seem to build simple models that are easy to learn to support planning and strategic exploration. Inspired by…

Motion planning is critical to realize the autonomous operation of mobile robots. As the complexity and randomness of robot application scenarios increase, the planning capability of the classical hierarchical motion planners is challenged.…

Visual Reinforcement Learning (RL) methods often require extensive amounts of data. As opposed to model-free RL, model-based RL (MBRL) offers a potential solution with efficient data utilization through planning. Additionally, RL lacks…

Offline learning is a key part of making reinforcement learning (RL) useable in real systems. Offline RL looks at scenarios where there is data from a system's operation, but no direct access to the system when learning a policy. Recent…

The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against…

Systems and machines undergo various failure modes that result in machine health degradation, so maintenance actions are required to restore them back to a state where they can perform their expected functions. Since maintenance tasks are…

In visuomotor policy learning, the control policy for the robotic agent is derived directly from visual inputs. The typical approach, where a policy and vision encoder are trained jointly from scratch, generalizes poorly to novel visual…

Continual reinforcement learning (CRL) refers to a naturalistic setting where an agent needs to endlessly evolve, by trial and error, to solve multiple tasks that are presented sequentially. One of the largest obstacles to CRL is that the…