相关论文: Temporal Action Representation Learning for Tactic…

In this paper, we address the discovery of robotic options from demonstrations in an unsupervised manner. Specifically, we present a framework to jointly learn low-level control policies and higher-level policies of how to use them from…

In many reinforcement learning tasks, the agent has to learn to interact with many objects of different types and generalize to unseen combinations and numbers of objects. Often a task is a composition of previously learned tasks (e.g.…

We study multi-agent reinforcement learning (MARL) for tasks in complex high-dimensional environments, such as autonomous driving. MARL is known to suffer from the \textit{partial observability} and \textit{non-stationarity} issues. To…

Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal processes do not have instantaneous relations. Although some…

Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the…

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…

Reinforcement learning (RL) is a promising approach. However, success is limited to real-world applications, because ensuring safe exploration and facilitating adequate exploitation is a challenge for controlling robotic systems with…

Environments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps…

Autonomous vehicles inevitably encounter a vast array of scenarios in real-world environments. Addressing long-tail scenarios, particularly those involving intensive interactions with numerous traffic participants, remains one of the most…

This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The…

In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of…

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE). We aim to…

Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to…

Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even…

Human-robot cooperation is essential in environments such as warehouses and retail stores, where workers frequently handle deformable objects like paper, bags, and fabrics. Coordinating robotic actions with human assistance remains…

Deep reinforcement learning has recently made significant progress in solving computer games and robotic control tasks. A known problem, though, is that policies overfit to the training environment and may not avoid rare, catastrophic…

We develop an algorithm for the motion and task planning of a system comprised of multiple robots and unactuated objects under tasks expressed as Linear Temporal Logic (LTL) constraints. The robots and objects evolve subject to uncertain…

Generative models such as diffusion models, excel at capturing high-dimensional distributions with diverse input modalities, e.g. robot trajectories, but are less effective at multi-step constraint reasoning. Task and Motion Planning (TAMP)…

This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is…

Shared autonomy provides an effective framework for human-robot collaboration that takes advantage of the complementary strengths of humans and robots to achieve common goals. Many existing approaches to shared autonomy make restrictive…