Výsledky vyhľadávania - Computing methodologies Machine learning Learning settings Learning from demonstrations

VMP: Versatile Motion Priors for Robustly Tracking Motion on Physical Characters Autor Serifi, Agon, Grandia, Ruben, Knoop, Espen, Gross, Markus, Bächer, Moritz

“…Recent progress in physics‐based character control has made it possible to learn policies from unstructured motion data. However, it remains challenging to…”
Získať plný text

Learning to Move Like Professional Counter‐Strike Players Autor Durst, D., Xie, F., Sarukkai, V., Shacklett, B., Frosio, I., Tessler, C., Kim, J., Taylor, C., Bernstein, G., Choudhury, S., Hanrahan, P., Fatahalian, K.

“…In multiplayer, first‐person shooter games like Counter‐Strike: Global Offensive (CS:GO), coordinated movement is a critical component of high‐level strategic…”
Získať plný text

Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data Autor Tappler, Martin, Pferscher, Andrea, Aichernig, Bernhard K., Konighofer, Bettina

“…Reinforcement learning from demonstrations (RLfD) is a promising approach to improve the exploration efficiency of reinforcement learning (RL…”
Získať plný text

Preference-Conditioned Language-Guided Abstraction Autor Peng, Andi, Bobu, Andreea, Li, Belinda Z., Sumers, Theodore R., Sucholutsky, Ilia, Kumar, Nishanth, Griffiths, Thomas L., Shah, Julie A.

“…Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations…”
Získať plný text

Aligning Human and Robot Representations Autor Bobu, Andreea, Peng, Andi, Agrawal, Pulkit, Shah, Julie A., Dragan, Anca D.

“… they must be aligned. We observe that current learning approaches suffer from representation misalignment, where the robot's learned representation does not capture the human's representation…”
Získať plný text

Feature Expansive Reward Learning: Rethinking Human Input Autor Bobu, Andreea, Wiggert, Marius, Tomlin, Claire, Dragan, Anca D.

“… Our insight is that rather than implicitly learning about the missing feature(s) from demonstrations, the robot should instead ask for data that explicitly teaches it about what…”
Získať plný text

Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation Autor Chen, Letian, Paleja, Rohan, Ghuy, Muyleng, Gombolay, Matthew

“… On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations…”
Získať plný text

Enhancing Safety in Learning from Demonstration Algorithms via Control Barrier Function Shielding Autor Yang, Yue, Chen, Letian, Zaidi, Zulfiqar, van Waveren, Sanne, Krishna, Arjun, Gombolay, Matthew

“…Learning from Demonstration (LfD) is a powerful method for non-roboticists end-users to teach robots new tasks, enabling them to customize the robot behavior…”
Získať plný text

Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning Autor Trinh, Tu, Chen, Haoyu, Brown, Daniel S.

“…? To address this problem, we propose a novel self-assessment approach based on Bayesian inverse reinforcement learning and value-at-risk, enabling learning-from-demonstration ("LfD…”
Získať plný text

Zero-Shot Learning to Enable Error Awareness in Data-Driven HRI Autor Ravishankar, Joshua, Doering, Malcolm, Kanda, Takayuki

“…Data-driven social imitation learning is a minimally-supervised approach to generating robot behaviors for human-robot interaction (HRI…”
Získať plný text

Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation Autor Daniele, Andrea F., Bansal, Mohit, Walter, Matthew R.

“… We first decide which information to share with the user according to their preferences, using a policy trained from human demonstrations…”
Získať plný text

Track-Assignment Detailed Routing Using Attention-based Policy Model With Supervision Autor Liao, Haiguang, Dong, Qingyi, Qi, Weiyi, Fallon, Elias, Kara, Levent Burak

“… In this work, we propose a machine learning driven method for solving the track-assignment detailed routing problem for advanced node analog circuits…”
Získať plný text

Autonomously Learning One-To-Many Social Interaction Logic from Human-Human Interaction Data Autor Nanavati, Amal, Doering, Malcolm, Brščić, Dražen, Kanda, Takayuki

“… Our proposed system for learning the interaction logic uses neural networks to first learn which customer actions are important to respond to and then learn how the shopkeeper should respond…”
Získať plný text

State-Aware Configuration Detection for Augmented Reality Step-by-Step Tutorials Autor Stanescu, Ana, Mohr, Peter, Kozinski, Mateusz, Mori, Shohei, Schmalstieg, Dieter, Kalkofen, Denis

“…Presenting tutorials in augmented reality is a compelling application area, but previous attempts have been limited to objects with only a small numbers of…”
Získať plný text

Sharing Model Framework for Zero‐Shot Sketch‐Based Image Retrieval Autor Ho, Yi‐Hsuan, Way, Der‐Lor, Shih, Zen‐Chung

“…Sketch‐based image retrieval (SBIR) is an emerging task in computer vision. Research interests have arisen in solving this problem under the realistic and challenging setting of zero‐shot learning…”
Získať plný text

Incremental learning of primitive skills from demonstration of a task Autor Sang Hyoung Lee, Hyung Kyu Kim, Il Hong Suh

“…In this work, we propose methods for automatically generating primitive skills from the demonstration of a task…”
Získať plný text

Encoding bi-manual coordination patterns from human demonstrations Autor Pais, Ana Lucia, Billard, Aude

“… hand configuration and grasp information. Secondly for learning the task we propose a method for extracting task constraints for each arm and coordination patterns between the arms…”
Získať plný text

Multi-thresholded approach to demonstration selection for interactive robot learning Autor Chernova, Sonia, Veloso, Manuela

“…Effective learning from demonstration techniques enable complex robot behaviors to be taught from a small number of demonstrations…”
Získať plný text

Enhancing Networked Embedded Systems Using Deep Learning Techniques Autor Asha, K, Kumar, Ritesh, Fiza, Samreen

“… In addition, using reinforcement learning helps systems behave and use energy more efficiently, creating a more flexible and smart setting…”
Získať plný text

Addressing Data Scarcity in the Medical Domain: A GPT-Based Approach for Synthetic Data Generation and Feature Extraction Autor Sufi, Fahim

“…This research confronts the persistent challenge of data scarcity in medical machine learning by introducing a pioneering methodology that harnesses the capabilities of Generative Pre-trained Transformers (GPT…”
Získať plný text