相关论文: Deep Predictive Policy Training using Reinforcemen…

Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…

Deep Reinforcement Learning is gaining increasing attention thanks to its capability to learn complex policies in high-dimensional settings. Recent advancements utilize a dual-network architecture to learn optimal policies through the…

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque, joint angle, or end-effector position. This forces the agent to make…

Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distribution. This limitation is especially important in…

Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for tasks where complex policies are learned within reactive systems. Unfortunately, these policies are known to be susceptible to bugs. Despite significant…

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve…

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on…

While solving complex manipulation tasks, manipulation policies often need to learn a set of diverse skills to accomplish these tasks. The set of skills is often quite multimodal - each one may have a quite distinct distribution of actions…

The behavior decision-making subsystem is a key component of the autonomous driving system, which reflects the decision-making ability of the vehicle and the driver, and is an important symbol of the high-level intelligence of the vehicle.…

Policy search can in principle acquire complex strategies for control of robots and other autonomous systems. When the policy is trained to process raw sensory inputs, such as images and depth maps, it can also acquire a strategy that…

Training robots with reinforcement learning (RL) typically involves heavy interactions with the environment, and the acquired skills are often sensitive to changes in task environments and robot kinematics. Transfer RL aims to leverage…

Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and…

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

This paper presents a technique for trajectory planning based on continuously parameterized high-level actions (motion primitives) of variable duration. This technique leverages deep reinforcement learning (Deep RL) to formulate a policy…

Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt…

While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for…

Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement…

Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algorithm, building on the CN2 rule mining algorithm, that…

In this paper we focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach. The work is based on the deep deterministic policy gradient (DDPG) algorithm, proven to be…