Simon Holk
YOU?
Author Swipe
View article: FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions
FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions Open
Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task. H…
View article: PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning
PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning Open
Preference-based reinforcement learning (RL) has emerged as a new field in\nrobot learning, where humans play a pivotal role in shaping robot behavior by\nexpressing preferences on different sequences of state-action pairs. However,\nformu…
View article: Aligning Human Preferences with Baseline Objectives in Reinforcement Learning
Aligning Human Preferences with Baseline Objectives in Reinforcement Learning Open
Practical implementations of deep reinforcement learning (deep RL) have been challenging due to an amplitude of factors, such as designing reward functions that cover every possible interaction. To address the heavy burden of robot reward …
View article: Dimensional perception of a ‘smiling McGurk effect’
Dimensional perception of a ‘smiling McGurk effect’ Open
Multisensory integration influences emotional perception, as the McGurk effect demonstrates for the communication between humans. Human physiology implicitly links the production of visual features with other modes like the audio channel: …
View article: Visualizing our galaxy using Virtual Reality and big data
Visualizing our galaxy using Virtual Reality and big data Open
Big data is becoming ever increasingly important in every kind of scientific field, and data visualization is a big part of gaining an understanding of the data. Exploring data builds on intuition but exploring some data on a 2D screen can…