相关论文: Hierarchically Decoupled Imitation for Morphologic…

Legged locomotion is a challenging task for learning algorithms, especially when the task requires a diverse set of primitive behaviors. To solve these problems, we introduce a hierarchical framework to automatically decompose complex…

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning accommodate teams of different sizes, heavily relying on the…

Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing…

Decision-making in robotics using denoising diffusion processes has increasingly become a hot research topic, but end-to-end policies perform poorly in tasks with rich contact and have limited controllability. This paper proposes…

We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically,…

Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and…

For robotic vehicles to navigate robustly and safely in unseen environments, it is crucial to decide the most suitable navigation policy. However, most existing deep reinforcement learning based navigation policies are trained with a…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage…

Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…

Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these…

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this…

Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a…

One approach for improving sample efficiency in cooperative multi-agent learning is to decompose overall tasks into sub-tasks that can be assigned to individual agents. We study this problem in the context of reward machines: symbolic tasks…

Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as…

We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning…

Methods of deep machine learning enable to to reuse low-level representations efficiently for generating more abstract high-level representations. Originally, deep learning has been applied passively (e.g., for classification purposes).…