Related papers: Skill Q-Network: Learning Adaptive Skill Ensemble …

While contemporary reinforcement learning research and applications have embraced policy gradient methods as the panacea of solving learning problems, value-based methods can still be useful in many domains as long as we can wrangle with…

Service robots are increasingly deployed in diverse and dynamic environments, where both physical layouts and social contexts change over time and across locations. In these unstructured settings, conventional navigation systems that rely…

Deep reinforcement learning for high dimensional, hierarchical control tasks usually requires the use of complex neural networks as functional approximators, which can lead to inefficiency, instability and even divergence in the training…

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…

Point goal navigation (PGN) is a mapless navigation approach that trains robots to visually navigate to goal points without relying on pre-built maps. Despite significant progress in handling complex environments using deep reinforcement…

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and…

Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained. They have been shown to…

This paper proposes an Improved Noisy Deep Q-Network (Noisy DQN) to enhance the exploration and stability of Unmanned Aerial Vehicle (UAV) when applying deep reinforcement learning in simulated environments. This method enhances the…

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and…

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of…

Reinforcement learning is nowadays a popular framework for solving different decision making problems in automated driving. However, there are still some remaining crucial challenges that need to be addressed for providing more reliable…

We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to…

Deep learning has been shown to be highly effective for automatic modulation classification (AMC), which is a pivotal technology for next-generation cognitive communications. Yet, existing deep learning methods for AMC often lack robust…

In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…

In contrast to humans and animals who naturally execute seamless motions, learning and smoothly executing sequences of actions remains a challenge in robotics. This paper introduces a novel skill-agnostic framework that learns to sequence…

The discovery of environmental knowledge depends on labeled task-specific data, but is often constrained by the high cost of data collection. Existing machine learning approaches usually struggle to generalize in data-sparse or atypical…

Currently decision making is one of the biggest challenges in autonomous driving. This paper introduces a method for safely navigating an autonomous vehicle in highway scenarios by combining deep Q-Networks and insight from control theory.…

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is…

Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep…