filmov
tv
Speeding up Deep Reinforcement Learning via Transfer and Multitask Learning
Показать описание
Speaker: Yunshu Du
Host: Gail Murphy
Research Presentation: Speeding up Deep Reinforcement Learning via Transfer and Multitask Learning
Deep Reinforcement learning (DeepRL) has been increasingly popular as a way of learning to control agents without needing to hand-craft inputs. Unfortunately, DeepRL algorithms often suffer from high time and data complexity, which can be problematic for real-world applications. Yunshu reviews the basics of reinforcement learning and deep learning, and then describe some of the challenges associated with training a DeepRL agent. Yunshu presents her research on how to leverage two approaches, transfer learning and multitask learning.
Mentoring Topic: How to Choose a Research Direction as an Undergraduate
While undergraduate research is rewarding, choosing the topic that suits you can be stressful. Yunshu shares her story of how she got involved in her current research interest, and will suggest what you should consider when looking for your first research project.
Originally hosted as part of the Virtual Undergraduate Town Hall Program, and interactive webinar experience.
October 4, 2018
Host: Gail Murphy
Research Presentation: Speeding up Deep Reinforcement Learning via Transfer and Multitask Learning
Deep Reinforcement learning (DeepRL) has been increasingly popular as a way of learning to control agents without needing to hand-craft inputs. Unfortunately, DeepRL algorithms often suffer from high time and data complexity, which can be problematic for real-world applications. Yunshu reviews the basics of reinforcement learning and deep learning, and then describe some of the challenges associated with training a DeepRL agent. Yunshu presents her research on how to leverage two approaches, transfer learning and multitask learning.
Mentoring Topic: How to Choose a Research Direction as an Undergraduate
While undergraduate research is rewarding, choosing the topic that suits you can be stressful. Yunshu shares her story of how she got involved in her current research interest, and will suggest what you should consider when looking for your first research project.
Originally hosted as part of the Virtual Undergraduate Town Hall Program, and interactive webinar experience.
October 4, 2018
1:11:04
Speeding up Deep Reinforcement Learning via Transfer and Multitask Learning
0:03:00
Training in Task Space to Speed Up and Guide Reinforcement Learning
0:19:14
A 24x Speedup for Reinforcement Learning with RLlib + Ray
0:24:05
Reinforcement Learning, Fast and Slow
0:25:35
2020 LLVM in HPC Workshop: Static Neural Compiler Optimization via Deep Reinforcement Learning
0:00:25
Landmark Detection in a 3D MR Image using Deep Reinforcement Learning
0:17:35
Deep Reinforcement Learning for Fluid Dynamics and Control
0:51:50
Accelerating Reinforcement Learning
0:08:40
AI Learns to Walk (deep reinforcement learning)
0:30:19
Practical applications of deep reinforcement learning using AnyLogic
0:57:55
MIT 6.S094: Deep Reinforcement Learning
0:00:58
Air Traffic Management with Deep Reinforcement Learning
0:01:01
Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning
0:34:56
Deep Reinforcement Learning for Driving Policy
1:27:30
MIT 6.S094: Deep Reinforcement Learning for Motion Planning
0:02:47
Autonomous Single Image Drone Exploration with Deep Reinforcement Learning and Mixed Reality
0:05:18
Large Batch Simulation for Deep Reinforcement Learning at ICLR 2021
0:20:50
Cooperative Deep Reinforcement Learning for Traffic Signal Control
1:06:34
Physics-Informed Deep Reinforcement Learning for Power System Optimization and Control
0:07:24
Massively Parallel Processing for Deep Reinforcement Learning
![[MOREL] Unsupervised Video](https://i.ytimg.com/vi/z8luZ3dHWbU/hqdefault.jpg)
0:48:57
[MOREL] Unsupervised Video Object Segmentation for Deep Reinforcement Learning
0:00:19
Deep Reinforcement Learning with experience replay in 15x15
0:22:11
Deep Reinforcement Learning on Intelligent Traffic System
0:38:23
Making Real-World Reinforcement Learning Practical
Комментарии