相关论文: Open-World Multi-Task Control Through Goal-Aware R…

An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?"…

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question…

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time…

Goal-conditioned navigation models for ground robots trained using supervised learning show promising zero-shot transfer, but their collision-avoidance capability nevertheless degrades under distribution shift, i.e. environmental, robot or…

The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on…

Enhancing AI systems with efficient communication skills for effective human assistance necessitates proactive initiatives from the system side to discern specific circumstances and interact aptly. This research focuses on a collective…

The advances in unsupervised object-centric representation learning have significantly improved its application to downstream tasks. Recent works highlight that disentangled object representations can aid policy learning in image-based,…

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic…

The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that…

Navigating social robots in dense, dynamic crowds is challenging due to environmental uncertainty and complex human-robot interactions. While Model Predictive Control (MPC) offers strong real-time performance, its reliance on a fixed…

Goal recognition is the problem of recognizing the intended goal of autonomous agents or humans by observing their behavior in an environment. Over the past years, most existing approaches to goal and plan recognition have been ignoring the…

The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when cooperation yields a better outcome. One well known reason…

Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Extensive research has focused on vision-to-language…

We consider an active visual exploration scenario, where an agent must intelligently select its camera motions to efficiently reconstruct the full environment from only a limited set of narrow field-of-view glimpses. While the agent has…

To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target squares. We find this network pursues multiple…

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on collecting new demonstrations for a specific task of interest…

Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Such agents need to create and represent goals, select which ones to pursue and learn to achieve them. Recent…