Related papers: Full Gradient Deep Reinforcement Learning for Aver…
We propose in this work the gradient-enhanced deep neural networks (DNNs) approach for function approximations and uncertainty quantification. More precisely, the proposed approach adopts both the function evaluations and the associated…
Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a highly versatile framework amenable to analytical results.…
We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation. Using the optimism principle and assuming that the MDP has a linear structure, we…
In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitations of DQN that prevent it from converging to good-quality…
The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…
Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full precision counterparts. To maintain the same performance level especially at low bit-widths,…
We propose risk-sensitive reinforcement learning algorithms catering to three families of risk measures, namely expectiles, utility-based shortfall risk and optimized certainty equivalent risk. For each risk measure, in the context of a…
Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function. Although wildly successful under laboratory conditions,…
Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance. In prior methods, policy and value networks are separately optimized using a disjoint network architecture…
We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…
Deep Q-Network (DQN) marked a major milestone for reinforcement learning, demonstrating for the first time that human-level control policies could be learned directly from raw visual inputs via reward maximization. Even years after its…
We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at…
This work presents the first finite-time analysis for the last-iterate convergence of average-reward $Q$-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsizes, which serve as…
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…
We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the…
Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the…
The Distributional Alignment Game framework provides a powerful variational perspective on Answer-Level Fine-Tuning (ALFT). However, standard algorithms for these games rely on estimating logarithmic rewards from small batches, introducing…
Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…
Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…
We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this…