Description
In the field of machine learning, reinforcement learning stands out for its ability to explore approaches to complex, high dimensional problems that outperform even expert humans. For robotic locomotion tasks reinforcement learning provides an approach to solving them without the need for unique controllers. In this thesis, two reinforcement learning algorithms, Deep Deterministic Policy Gradient and Group Factor Policy Search are compared based upon their performance in the bipedal walking environment provided by OpenAI gym. These algorithms are evaluated on their performance in the environment and their sample efficiency.
Included in this item (2)
Permanent Link
Permanent Link
Permanent Link
Details
Title
- Deep Periodic Networks
Contributors
Agent
- McDonald, Dax (Author)
- Ben Amor, Heni (Thesis director)
- Yang, Yezhou (Committee member)
- Barrett, The Honors College (Contributor)
- Computer Science and Engineering Program (Contributor)
Date Created
The date the item was original created (prior to any relationship with the ASU Digital Repositories.)
2018-12
Collections this item is in