research
∙
07/21/2023
Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning
Reinforcement Learning (RL) has been widely explored in Traffic Signal C...
share
research
∙
04/14/2023
Learning Perceptive Bipedal Locomotion over Irregular Terrain
In this paper we propose a novel bipedal locomotion controller that uses...
research
∙
10/11/2022
Factors of Influence of the Overestimation Bias of Q-Learning
We study whether the learning rate α, the discount factor γ and the rewa...
research
∙
09/07/2022
Machine Learning Students Overfit to Overfitting
Overfitting and generalization is an important concept in Machine Learni...
research
∙
08/09/2022
How Well Do Vision Transformers (VTs) Transfer To The Non-Natural Image Domain? An Empirical Study Involving Art Classification
Vision Transformers (VTs) are becoming a valuable alternative to Convolu...
research
∙
06/21/2022
Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking
Reinforcement learning (RL) for traffic signal control (TSC) has shown b...
research
∙
05/28/2022
Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning
Recent progress in deep model-based reinforcement learning allows agents...
research
∙
10/06/2021
On The Transferability of Deep-Q Networks
Transfer Learning (TL) is an efficient machine learning paradigm that al...
research
∙
08/14/2021
Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
Reinforcement learning (RL) is well known for requiring large amounts of...
research
∙
12/22/2020
QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
This paper introduces four new algorithms that can be used for tackling ...
research
∙
05/11/2020
On the Transferability of Winning Tickets in Non-Natural Image Datasets
We study the generalization properties of pruned neural networks that ar...
research
∙
09/01/2019
Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning algorithms
This paper makes one step forward towards characterizing a new family of...
research
∙
09/30/2018