相关论文: Experience Filter: Using Past Experiences on Unsee…

In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…

Autonomous agents operating around human actors must consider how their behaviors might affect those humans, even when not directly interacting with them. To this end, it is often beneficial to be predictable and appear naturalistic.…

Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…

To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting…

Deep reinforcement learning (RL) policies, although optimal in terms of task rewards, may not align with the personal preferences of human users. To ensure this alignment, a naive solution would be to retrain the agent using a reward…

Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based methods---such as deep…

Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert…

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…

Zero-shot human-AI coordination is the training of an ego-agent to coordinate with humans without human data. Most studies on zero-shot human-AI coordination have focused on enhancing the ego-agent's coordination ability in a given…

Deep Reinforcement Learning (RL) models often fail to generalize when even small changes occur in the environment's observations or task requirements. Addressing these shifts typically requires costly retraining, limiting the reusability of…

Model-free reinforcement learning has emerged as a powerful method for developing robust robot control policies capable of navigating through complex and unstructured environments. The effectiveness of these methods hinges on two essential…

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is…

Reinforcement learning has been applied to a wide variety of robotics problems, but most of such applications involve collecting data from scratch for each new task. Since the amount of robot data we can collect for any single task is…

Modern neural collaborative filtering techniques are critical to the success of e-commerce, social media, and content-sharing platforms. However, despite technical advances -- for every new application domain, we need to train an NCF model…

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

Coordination among connected and autonomous vehicles (CAVs) is advancing due to developments in control and communication technologies. However, much of the current work is based on oversimplified and unrealistic task-specific assumptions,…

Active traffic management with autonomous vehicles offers the potential for reduced congestion and improved traffic flow. However, developing effective algorithms for real-world scenarios requires overcoming challenges related to…

This article proposes a hierarchical learning architecture for safe data-driven control in unknown environments. We consider a constrained nonlinear dynamical system and assume the availability of state-input trajectories solving control…

We present a system for non-prehensile manipulation that require a significant number of contact mode transitions and the use of environmental contacts to successfully manipulate an object to a target location. Our method is based on deep…