arXiv research

Deep-RLS uses deep learning to improve PCA for better source separation.

This paper surveys RL for combinatorial optimization, focusing on TSP.

Proposes deep-RL with GANs for ultra-reliable low-latency communication.

RADIAL-RL improves deep RL agents' robustness against adversarial attacks.

Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstab…

Deep RL strategy improves natural gas trading performance.

Survey of deep RL in intelligent transportation systems.

We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep…

Deep RL agents suffer from transient non-stationarity, which ITER mitigates.

Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and e…

This paper shows using classification instead of regression improves deep RL scalability.

PriMORL trains private RL policies on offline data.

Optimistic RL algorithms are simplified for deep RL with competitive performance.

Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to di…

Deep RL controls anesthesia more accurately than traditional methods.

New RL theory predicts deep RL success based on greedy actions under random policies.

HyperAgent improves RL exploration in large-scale problems.

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional systems. However, in order to be reliable in highly dynamic urban areas, such cont…

Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators. These results suggest that RL methods that use temporal differencing (TD) are superior to direct Monte Carlo estimation (M…

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, roboti…

Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently,…

In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rap…

Increasing input dimensionality improves deep RL performance and sample efficiency.

Deep hedging uses RL to minimize risk in financial markets.

New RL framework simulates financial market dynamics.

New method defends RL agents from poisoning attacks without MDP knowledge.

Deep RL algorithms can overfit to early experiences, leading to poor performance.

SF-DQN improves RL transfer by learning successor features.

Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep RL suffers from high sensitivity to noisy, incomplete, and misleading…

Recent years have witnessed significant progresses in deep Reinforcement Learning (RL). Empowered with large scale neural networks, carefully designed architectures, novel training algorithms and massively parallel computing devices, researchers are able to attack many challenging RL problems. However, in machine learn…

Model-free deep reinforcement learning (RL) algorithms have been widely used for a range of complex control tasks. However, slow convergence and sample inefficiency remain challenging problems in RL, especially when handling continuous and high-dimensional state spaces. To tackle this problem, we propose a general acce…

Automatically generates a deep RL curriculum for faster and more stable learning.

Improves deep RL agents' generalization to unseen environments.

Study analyzes sensitivity of RL algorithm for ICU hemodynamic management.

Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL agent to manage the operation of storage devices in a household and is designed to maximize demand-side cost savings. The proposed technique is data-driven, and the RL agent learns from scratch how to efficiently use the energ…

Paper analyzes sample complexity for offline RL with deep ReLU networks.

Automates RL with sample-efficient hyperparameter optimization.

Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted t…

Deep RL improves Diplomacy performance, outperforming previous methods.

Deep reinforcement learning (deep RL) holds the promise of automating the acquisition of complex controllers that can map sensory inputs directly to low-level actions. In the domain of robotic locomotion, deep RL could enable learning locomotion skills with minimal engineering and without an explicit model of the robot…

Adaptive traffic control uses deep RL to improve decision-making.

AdaStop improves statistical testing for Deep RL algorithm comparisons.

New RL algorithm explains why deep learning works in stochastic environments.

Equivariant CNNs improve RL performance in symmetric environments.

Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a growing interest in both research and industrial communities in the promising potentials of this paradigm. The list of current and envisioned applications of deep RL ranges from autonomous navigation and robotics to control applicatio…

Paper develops neural network approximation for pessimistic offline RL with theoretical guarantees.

The paper identifies overfitting as the main bottleneck in efficient deep reinforcement learning.

Improved RL for grasping in cluttered scenes using state representation learning.