Related papers: Generalizing Multi-Step Inverse Models for Represe…

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…

In data-driven inverse optimization an observer aims to learn the preferences of an agent who solves a parametric optimization problem depending on an exogenous signal. Thus, the observer seeks the agent's objective function that best…

Deep reinforcement learning is quickly changing the field of artificial intelligence. These models are able to capture a high level understanding of their environment, enabling them to learn difficult dynamic tasks in a variety of domains.…

Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning.…

Representation learning methods are an important tool for addressing the challenges posed by complex observations spaces in sequential decision making problems. Recently, many methods have used a wide variety of types of approaches for…

When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due…

Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative…

This work aims to improve generalization and interpretability of dynamical systems by recovering the underlying lower-dimensional latent states and their time evolutions. Previous work on disentangled representation learning within the…

This work introduces a non-intrusive model reduction approach for learning reduced models from partially observed state trajectories of high-dimensional dynamical systems. The proposed approach compensates for the loss of information due to…

In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as…

Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of robotics. The ability to predict outcomes of interactions with objects is paramount in this setting.…

Growing concerns regarding the operational usage of AI models in the real-world has caused a surge of interest in explaining AI models' decisions to humans. Reinforcement Learning is not an exception in this regard. In this work, we propose…

Manually specifying features that capture the diversity in traffic environments is impractical. Consequently, learning-based agents cannot realize their full potential as neural motion planners for autonomous vehicles. Instead, this work…

Effective control requires knowledge of the process dynamics to guide the system toward desired states. In many control applications this knowledge is expressed mathematically or through data-driven models, however, as complexity grows…

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model…

Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based…

Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for…

We propose a method to teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain. The method learns a policy for directing existing information retrieval and machine reading…

We address the problem of learning reusable state representations from streaming high-dimensional observations. This is important for areas like Reinforcement Learning (RL), which yields non-stationary data distributions during training. We…

The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for…