Orr Krupnik
Orr Krupnik
Robot Learning Research
Robot Learning Research
Robotics, Reinforcement Learning and Generative Models
Robotics, Reinforcement Learning and Generative Models
Embedded Files
About Me
About Me
I am a robotics and reinforcement learning researcher with a focus on model-based RL. I am interested in finding ways in which we can apply prior knowledge of the world to enhance robot learning, leverageing generative models and fast GPU-based physics simulation.
I have completed my PhD (direct track) at the Electrical and Computer Engineering Department at Technion - Israel Institute of Technology, advised by Prof. Aviv Tamar and affiliated with the Reinforcement Learning Research Labs.
In 2017, I received my BSc. in Computer and Software Engineering (cum laude) from the Electrical and Computer Engineering Department at Technion.
Publications
Publications
MAMBA: An Effective World Model Approach for Meta-Reinforcement Learning
MAMBA: An Effective World Model Approach for Meta-Reinforcement Learning
Fine-Tuning Generative Models as an Inference Method for Robotic Tasks
Fine-Tuning Generative Models as an Inference Method for Robotic Tasks
QueuePilot: Reviving Small Buffers with a Learned AQM Policy
QueuePilot: Reviving Small Buffers with a Learned AQM Policy
Multi-Agent Reinforcement Learning with Multi-Step Generative Models
Multi-Agent Reinforcement Learning with Multi-Step Generative Models
Other Projects
Other Projects
A Reinforcement Learning Approach to Robotic Bin Packing
A Reinforcement Learning Approach to Robotic Bin Packing
Page updated
Google Sites
Report abuse