Are you interested in machine learning for intelligent decision making? Would you like to overcome fundamental challenges and bridge the gap to physical agents like robots, autonomous cars or automated factories? Create new cutting edge neural network architectures to empirically solve theoretical problems in artificial intelligence? Think about broader implications and practical applications?
Deep reinforcement learning (RL) has been at the core of many recent success stories in AI, in particular for playing strategic games like Go, Chess and StarCraft. Despite those spectacular breakthroughs, RL is rarely used in practice, as the learned control policies are generally not assumed to be reliable enough for deployed robots or autonomous cars. We want to change that!
During your PhD, you will develop new algorithms which generalize to situations that differ significantly from training. This will be possible by controlling a graph neural network's internal epistemic uncertainty, that is, how much the network trusts it's own computations. You will evaluate your work on multi-task RL benchmarks, where the agent learns one policy that is able to solve more than one task. Examples are simulated Mujoco robots or different levels of the same computer game. Your challenge will be to study, propose and empirically verify the properties that improve generalization in these benchmarks. You will be collaborating with other members of the Algorithmics group that work on related projects. There might also be an opportunity to transfer your work to real robots, if you are interested
Similar Positions
-
Ph D Student In Robotics And Artificial Intelligence, Luleå University of Technology, Sweden, about 1 month ago
26 Mar 2024 Job Information Organisation/Company Luleå University of Technology Research Field Engineering » Other Researcher Profile First Stage Researcher (R1) Country Sweden Application Deadlin...
-
Ph D Position Safe Planning And Control For Autonomous Robots, Delft University of Technology, Netherlands, about 15 hours ago
How can autonomous robots prove that their plans are always safe? Ensuring safe planning and control is paramount when we deploy autonomous robots in complex environments around humans, such as in...
-
Ph D Position Reinforcement Learning For Digital Finance, University of Twente (UT), Netherlands, about 1 month ago
26 Mar 2024 Job Information Organisation/Company University of Twente (UT) Research Field Cultural studies Researcher Profile First Stage Researcher (R1) Country Netherlands Application Deadline 3...
-
Ph D Position In Robotic System Integration For Musculoskeletal Robotic Hands , ETH Zurich, Switzerland, about 4 hours ago
100%, Zurich, fixed-term Project background The future of robotic manipulation lies in the development of systems that closely mimic the complex structures and capabilities of the human hand. Trad...
-
Ph D's On Neuromorphic Computing & Engineering: Algorithms&Hardware Architectures, Eindhoven University of Technology (TU/e), Netherlands, 28 days ago
28 Mar 2024 Job Information Organisation/Company Eindhoven University of Technology (TU/e) Research Field Technology Researcher Profile First Stage Researcher (R1) Country Netherlands Application ...
-
Ph D's On Neuromorphic Computing & Engineering: Algorithms&Hardware Architectures, Eindhoven University of Technology, Netherlands, about 17 hours ago
Irène Curie Fellowship No Department(s) Electrical Engineering Reference number V36.7370 Job description The Neuromorphic Edge Computing Systems (NECS) Lab at the Eindhoven University of Technolog...