In situ compression artifact removal in scientific data using deep transfer learning and experience replay

Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay

The process for transferring knowledge of multiple reinforcement learning policies into a single multi-task policy via distillation technique is known as policy distillation. When policy distillation is under a deep reinforcement learning setting, due to the giant parameter size and the huge state space for each task domain, it requires extensive computational efforts to train the multi-task po...

Enhanced Experience Replay for Deep Reinforcement Learning

Deep In-GPU Experience Replay

Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copi...

pattern recognition in maintenance data using methodologies data minitng (cade study isfahan regional power electric company)

فعالیت های نگهداری و تعمیرات اطلاعاتی را تولید می کند که می تواند در تعیین زمان های بیکاری و ارایه یک برنامه زمان بندی شده یا تعیین هشدارهای خرابی به پرسنل نگهداری و تعمیرات کمک کند. وقتی که مقدار داده های تولید شده زیاد باشند، فهم بین متغیرها بسیار مشکل می شوند. این پایان نامه به کاربردی از داده کاوی برای کاوش پایگاه های داده چندبعدی در حوزه نگهداری و تعمیرات، برای پیدا کردن خرابی هایی که موجب...

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on singleagent RL to the multi-agent setting. A key stumbling block is that indep...