Bekijk het profiel van Aske Plaat op LinkedIn, de grootste professionele community ter wereld. Aske heeft 12 functies op zijn of haar profiel. Bekijk het volledige profiel op LinkedIn om de connecties van Aske en vacatures bij vergelijkbare bedrijven te blogger.com: Professor & Scientific Director of I would like to thank Aske Plaat for giving me the motivation to go with my instincts, and pick a thesis subject in arti cial intelligence. I am also grateful to Jeroen Unger for giving me the freedom to investigate deep learning during my internship at Microsoft. Furthermore, a big In the Spring I teach Reinforcement Learning in the Master Computer Science (since ). Book & teaching materials are online (click here). For all questions, please go to Brightspace. In the Fall I teach a Seminar on Advanced Deep Reinforcement Learning in the Master Computer Science (, ). Enrollment is limited; send me email. Click
Aske Plaat - Google Scholar
If you are a student ready for your master's thesis, feel free to contact any member of the RL group, which you may find under Team.
Below you can find a list of open master's thesis topics. Supervisor : Mike Preuss. Supervisor : Aske Plaat. Summary : AlphaZero has taught itself to play world-class Go from scratch using a form of reinforcement learning called curriculum learning.
Supervisor : Thomas Moerland. Summary : Standard planning approaches use forward methods, aske plaat thesis. However, that seems counterintuitive to the way humans tend to plan outside of boardgames like Chess. Instead, we first sample a distant goal, and then aske plaat thesis inpaint different trajectories between start and goal state, for example starting by fixing a goal halfway. In this project, we will look at this new approach towards hierarchical planning see, e.
pdf for a first attempt. Summary : Exploration is a key topic in reinforcement learning. A popular approach is through the use of intrinsic motivation, which for example explores like children based on curiosity and novelty. Supervisor : Peter van der PuttenAske Plaat, Mike Preuss.
Summary : AI techniques such as reinforcement learning can be very powerful methods to optimize certain given objectives, aske plaat thesis, but unfortunately humans are notable bad at stating their objectives and constraints well enough, or overseeing the side effects of maximizing these objectives. In reinforcement learning this problem is known as specification gaming — which actually is a misnomer as the AI is simply blindly trying to optimize the given objective.
A more general term is value alignment — how can we make sure that the AI aligns its values with ours. In this project we want to provide a compelling example of specification gaming, to make the public further aware of this key existential risk of AI. Optionally, aske plaat thesis, we can look into finding solutions, aske plaat thesis, for example by accepting that objectives specifications are initially flawed, but humans can adapt these on the way.
Search this site. Supervisor : Aske Plaat Summary : AlphaZero has taught itself to play world-class Go from scratch using a form of reinforcement learning called curriculum learning.
Supervisor : Thomas Moerland Summary : Standard planning approaches use forward methods, i. Supervisor : Thomas Moerland Summary : Exploration is a key topic in reinforcement learning. Report abuse. Page details. Page updated. Google Aske plaat thesis.
Everything you want to know about binding your PhD Thesis!
, time: 4:55Resume of Aske Plaat
blogger.com Aske Plaat obtained his PhD in Artif icial Intelligence from the University of Alberta, Edmonton, Canada. His work focused on search algorithms. After his graduation, he did post-doctoral research on the Cild system in combining supercomputing technologies group at the MIT Lab for Computer blogger.com he was awarded the Izaak Walton Killam Memorial Postdoctoral Fellowship, and an I would like to thank Aske Plaat for giving me the motivation to go with my instincts, and pick a thesis subject in arti cial intelligence. I am also grateful to Jeroen Unger for giving me the freedom to investigate deep learning during my internship at Microsoft. Furthermore, a big Supervisor: Peter van der Putten, Aske Plaat, Mike Preuss. Summary: AI techniques such as reinforcement learning can be very powerful methods to optimize certain given objectives, but unfortunately humans are notable bad at stating their objectives and constraints well enough, or overseeing the side effects of maximizing these objectives
No comments:
Post a Comment