Picture for Taku Yamagata

Taku Yamagata

Intelligent System Laboratory, University of Bristol

Safe and Robust Reinforcement Learning: Principles and Practice

Mar 30, 2024
Figure 1 for Safe and Robust Reinforcement Learning: Principles and Practice
Figure 2 for Safe and Robust Reinforcement Learning: Principles and Practice
Viaarxiv icon

When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations

Feb 06, 2023
Figure 1 for When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
Figure 2 for When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
Figure 3 for When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
Figure 4 for When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
Viaarxiv icon

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

Add code
Sep 08, 2022
Figure 1 for Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
Figure 2 for Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
Figure 3 for Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
Figure 4 for Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
Viaarxiv icon

Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills

Nov 16, 2021
Figure 1 for Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills
Figure 2 for Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills
Figure 3 for Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills
Figure 4 for Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills
Viaarxiv icon

Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control

Oct 13, 2020
Figure 1 for Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control
Figure 2 for Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control
Figure 3 for Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control
Figure 4 for Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control
Viaarxiv icon

Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback

Aug 16, 2019
Figure 1 for Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
Figure 2 for Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
Figure 3 for Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
Viaarxiv icon