Related papers: Wasserstein Flow Meets Replicator Dynamics: A Mean…
This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear…
This paper proposes a reinforcement learning (RL)-based backstepping control strategy to achieve fixed time consensus in nonlinear multi-agent systems with strict feedback dynamics. Agents exchange only output information with their…
Model-free deep reinforcement learning (RL) has been successfully applied to challenging continuous control domains. However, poor sample efficiency prevents these methods from being widely used in real-world domains. This paper introduces…
In this paper, we propose actor-director-critic, a new framework for deep reinforcement learning. Compared with the actor-critic framework, the director role is added, and action classification and action evaluation are applied…
Actors and critics in actor-critic reinforcement learning algorithms are functionally separate, yet they often use the same network architectures. This case study explores the performance impact of network sizes when considering actor and…
We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…
We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…
We present the first class of policy-gradient algorithms that work with both state-value and policy function-approximation, and are guaranteed to converge under off-policy training. Our solution targets problems in reinforcement learning…
We investigate the neural Actor Critic algorithm using shallow neural networks for both the Actor and Critic models. The focus of this work is twofold: first, to compare the convergence properties of the network outputs under various…
Estimating causal effects from observational data has become increasingly critical in diverse fields including healthcare, economics, and social policy. The fundamental challenge in causal inference arises from the missing counterfactuals…
Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of…
Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the…
Soft Actor Critic (SAC) algorithms show remarkable performance in complex simulated environments. A key element of SAC networks is entropy regularization, which prevents the SAC actor from optimizing against fine grained features,…
Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been…
We analyze an algorithm to numerically solve the mean-field optimal control problems by approximating the optimal feedback controls using neural networks with problem specific architectures. We approximate the model by an $N$-particle…
Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an…
In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update…
We study the machine learning task for models with operators mapping between the Wasserstein space of probability measures and a space of functions, like e.g. in mean-field games/control problems. Two classes of neural networks, based on…
Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of…