Search Results for author:
Found 14 papers, 6 papers with code
VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts
While more sophisticated exploration strategies can excel in specific, often sparse reward environments, existing simpler approaches, such as $\epsilon$-greedy, persist in outperforming them across a broader spectrum of domains.
Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation
Recommendation systems, for documents, have become tools to find relevant content on the Web.
Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning
Subsequently, we evaluated the performance of the two methods on a separate model of the same intersection that was developed with a different traffic simulator.
Factors of Influence of the Overestimation Bias of Q-Learning
We study whether the learning rate $\alpha$, the discount factor $\gamma$ and the reward signal $r$ have an influence on the overestimation bias of the Q-Learning algorithm.
Machine Learning Students Overfit to Overfitting
Overfitting and generalization is an important concept in Machine Learning as only models that generalize are interesting for general applications.
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 Convolutional Neural Networks (CNNs) when it comes to problems involving high-dimensional and spatially organized inputs such as images.
Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking
We present an approach to ensure safety in a real-world intersection by using an action space that is safe by design.
Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning
A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task.
On The Transferability of Deep-Q Networks
Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets.
Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks.
Model-based Reinforcement Learning
reinforcement-learning
+2
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 multi-agent reinforcement learning (MARL) problems occurring in cooperative settings.
On the Transferability of Winning Tickets in Non-Natural Image Datasets
We study the generalization properties of pruned neural networks that are the winners of the lottery ticket hypothesis on datasets of natural images.
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 \textit{model-free} Deep Reinforcement Learning (DRL) algorithms.
Deep Quality-Value (DQV) Learning
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning.
