Search Results for author: Julie Iskander

Found 5 papers, 0 papers with code

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

no code implementations21 Aug 2020 Mohammed Hossny, Julie Iskander

In this work we address the error propagation problem by introducing an iterative training procedure for deep reinforcement learning which allows the agent to learn a finite set of actions and how to coordinate between them in order to achieve a stable standing posture.

reinforcement-learning Reinforcement Learning (RL)

An ocular biomechanics environment for reinforcement learning

no code implementations12 Aug 2020 Julie Iskander, Mohammed Hossny

Reinforcement learning has been applied to human movement through physiologically-based biomechanical models to add insights into the neural control of these movements; it is also useful in the design of prosthetics and robotics.

Position reinforcement-learning +1

Refined Continuous Control of DDPG Actors via Parametrised Activation

no code implementations4 Jun 2020 Mohammed Hossny, Julie Iskander, Mohammed Attia, Khaled Saleh

In this paper, we propose enhancing actor-critic reinforcement learning agents by parameterising the final actor layer which produces the actions in order to accommodate the behaviour discrepancy of different actuators, under different load conditions during interaction with the environment.

Continuous Control OpenAI Gym +3

Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Data

no code implementations22 May 2019 Khaled Saleh, Ahmed Abobakr, Mohammed Attia, Julie Iskander, Darius Nahavandi, Mohammed Hossny

We have evaluated the performance of our proposed framework on the task of vehicle detection from a bird's eye view (BEV) point cloud images coming from real 3D LiDAR sensors.

Unsupervised Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.