相关论文: Learning 3D Navigation Protocols on Touch Interfac…

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on…

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests…

First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor virtual home-environment pose significant sample-efficiency challenges for reinforcement learning (RL) agents learning from sparse task…

Embodied agents operating in human spaces must be able to master how their environment works: what objects can the agent use, and how can it use them? We introduce a reinforcement learning approach for exploration for interaction, whereby…

Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control. Recently released…

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby,…

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of…

The optimal discrimination of coherent states of light with current technology is a key problem in classical and quantum communication, whose solution would enable the realization of efficient receivers for long-distance communications in…

Despite the potential of reinforcement learning (RL) for building general-purpose robotic systems, training RL agents to solve robotics tasks still remains challenging due to the difficulty of exploration in purely continuous action spaces.…

Adapting the user interface (UI) of software systems to meet the needs and preferences of users is a complex task. The main challenge is to provide the appropriate adaptations at the appropriate time to offer value to end-users. Recent…

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…

Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running. However, designing robust controllers for highly agile dynamic motions remains a substantial challenge for…

Artificial touch would seem well-suited for Reinforcement Learning (RL), since both paradigms rely on interaction with an environment. Here we propose a new environment and set of tasks to encourage development of tactile reinforcement…

Learning generalizable robot manipulation policies, especially for complex multi-fingered humanoids, remains a significant challenge. Existing approaches primarily rely on extensive data collection and imitation learning, which are…

Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy of 3D representations with 2D representations across…

Reinforcement learning (RL) has recently been used for solving challenging decision-making problems in the context of automated driving. However, one of the main drawbacks of the presented RL-based policies is the lack of safety guarantees,…

Existing automatic 3D image segmentation methods usually fail to meet the clinic use. Many studies have explored an interactive strategy to improve the image segmentation performance by iteratively incorporating user hints. However, the…

Human-robot collaboration is an essential research topic in artificial intelligence (AI), enabling researchers to devise cognitive AI systems and affords an intuitive means for users to interact with the robot. Of note, communication plays…

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…