Related papers: HyperPPO: A scalable method for finding small poli…

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Model-based planners and controllers are commonly used to solve complex manipulation problems as they can efficiently optimize diverse objectives and generalize to long horizon tasks. However, they often fail during deployment due to noisy…

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implement such a mapping via a neural network (NN) whose parameters…

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements. We introduce Regularized Hierarchical Policy Optimization (RHPO) to improve…

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system…

Deep reinforcement learning could be used to learn dexterous robotic policies but it is challenging to transfer them to new robots with vastly different hardware properties. It is also prohibitively expensive to learn a new policy from…

Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement learning models remains challenging. As one of the most…

Recognizing the substantial computational cost of backpropagation (BP), non-BP methods have emerged as attractive alternatives for efficient learning on emerging neuromorphic systems. However, existing non-BP approaches still face critical…

We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods, HYPPO uses adaptive surrogate models and directly accounts…

Studies that broaden drone applications into complex tasks require a stable control framework. Recently, deep reinforcement learning (RL) algorithms have been exploited in many studies for robot control to accomplish complex tasks.…

Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this…

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by hardware and speed constraints. Conventional model compression…

Robots equipped with rich sensing modalities (e.g., RGB-D cameras) performing long-horizon tasks motivate the need for policies that are highly memory-efficient. State-of-the-art approaches for controlling robots often use memory…

We present an algorithm for the control of complex networks and other nonlinear, high-dimensional dynamical systems. The computational approach is based on the recently-introduced concept of compensatory perturbations -- intentional…

In this work we present a method for learning a reactive policy for a simple dynamic locomotion task involving hard impact and switching contacts where we assume the contact location and contact timing to be unknown. To learn such a policy,…

In cooperative Multi-Agent Reinforcement Learning (MARL), efficient exploration is crucial for optimizing the performance of joint policy. However, existing methods often update joint policies via independent agent exploration, without…