The core challenge of offline reinforcement learning (RL) is dealing wit...
As with any machine learning problem with limited data, effective offlin...
We explore the problem of imitation learning (IL) in the context of
mean...
Knowledge distillation is commonly used for compressing neural networks ...
Despite the seeming success of contemporary grounded text generation sys...
This paper investigates model robustness in reinforcement learning (RL) ...
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leible...
We consider the Imitation Learning (IL) setup where expert data are not
...
Robust Markov decision processes (MDPs) aim to handle changing or partia...
We study the sample complexity of obtaining an ϵ-optimal policy in
Robus...
We present a novel robust policy gradient method (RPG) for s-rectangular...
Modern Deep Reinforcement Learning (RL) algorithms require estimates of ...
Mean-field games have been used as a theoretical tool to obtain an
appro...
Given a particular embodiment, we propose a novel method (C3PO) that lea...
The designs of many large-scale systems today, from traffic routing
envi...
In this work, we consider and analyze the sample complexity of model-fre...
Non-cooperative and cooperative games with a very large number of player...
Energy-based models, a.k.a. energy networks, perform inference by optimi...
Traditionally, Reinforcement Learning (RL) aims at deciding how to act
o...
In Reinforcement Learning (RL), discrete actions, as opposed to continuo...
Robust Markov decision processes (MDPs) aim to handle changing or partia...
Several algorithms have been proposed to sample non-uniformly the replay...
Mean Field Games (MFGs) can potentially scale multi-agent systems to
ext...
The Q-function is a central quantity in many Reinforcement Learning (RL)...
We use functional mirror ascent to propose a general framework (referred...
Offline Reinforcement Learning (RL) aims at learning an optimal control ...
We propose to learn to distinguish reversible from irreversible actions ...
Concave Utility Reinforcement Learning (CURL) extends RL from linear to
...
Adversarial imitation learning has become a popular framework for imitat...
We address the issue of tuning hyperparameters (HPs) for imitation learn...
We present a method enabling a large number of agents to learn how to fl...
Offline Reinforcement Learning methods seek to learn a policy from logge...
We address scaling up equilibrium computation in Mean Field Games (MFGs)...
In this paper we apply Deep Reinforcement Learning (Deep RL) and Domain
...
Despite definite success in deep reinforcement learning problems,
actor-...
Self-imitation learning is a Reinforcement Learning (RL) method that
enc...
Bootstrapping is a core mechanism in Reinforcement Learning (RL). Most
a...
In this paper, we deepen the analysis of continuous time Fictitious Play...
The study of exploration in Reinforcement Learning (RL) has a long histo...
In recent years, on-policy reinforcement learning (RL) has been successf...
Imitation Learning (IL) methods seek to match the behavior of an agent w...
Policy evaluation algorithms are essential to reinforcement learning due...
Building upon the formalism of regularized Markov decision processes, we...
Most of the research effort on image-based place recognition is designed...
We adapt the optimization's concept of momentum to reinforcement learnin...
Dynamic Programming (DP) provides standard algorithms to solve Markov
De...
This work demonstrates how to leverage previous network expert demonstra...
The ability to transfer representations to novel environments and tasks ...
This paper introduces a novel feature detector based only on information...
The theory of Mean Field Games (MFG) allows characterizing the Nash
equi...