作者
Adarsh Sehgal, Hung La, Sushil Louis, Hai Nguyen
发表日期
2019/2/25
研讨会论文
2019 Third IEEE International Conference on Robotic Computing (IRC)
页码范围
596-601
出版商
IEEE
简介
Reinforcement learning (RL) enables agents to take decision based on a reward function. However, in the process of learning, the choice of values for learning algorithm parameters can significantly impact the overall learning process. In this paper, we use a genetic algorithm (GA) to find the values of parameters used in Deep Deterministic Policy Gradient (DDPG) combined with Hindsight Experience Replay (HER), to help speed up the learning agent. We used this method on fetch-reach, slide, push, pick and place, and door opening in robotic manipulation tasks. Our experimental evaluation shows that our method leads to better performance, faster than the original algorithm.
学术搜索中的文章
A Sehgal, H La, S Louis, H Nguyen - 2019 Third IEEE International Conference on Robotic …, 2019