Search Results for author:
Found 6 papers, 3 papers with code
Structure in Reinforcement Learning: A Survey and Open Problems
We amalgamate these diverse methodologies under a unified framework, shedding light on the role of structure in the learning problem, and classify these methods into distinct patterns of incorporating structure.
AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks
The fields of both Natural Language Processing (NLP) and Automated Machine Learning (AutoML) have achieved remarkable results over the past years.
Learning Activation Functions for Sparse Neural Networks
By conducting experiments on popular DNN models (LeNet-5, VGG-16, ResNet-18, and EfficientNet-B0) trained on MNIST, CIFAR-10, and ImageNet-16 datasets, we show that the novel combination of these two approaches, dubbed Sparse Activation Function Search, short: SAFS, results in up to 15. 53%, 8. 88%, and 6. 33% absolute improvement in the accuracy for LeNet-5, VGG-16, and ResNet-18 over the default training protocols, especially at high pruning ratios.
AutoRL Hyperparameter Landscapes
Addressing an important open question on the legitimacy of such dynamic AutoRL approaches, we provide thorough empirical evidence that the hyperparameter landscapes strongly vary over time across representative algorithms from RL literature (DQN, PPO, and SAC) in different kinds of environments (Cartpole, Bipedal Walker, and Hopper) This supports the theory that hyperparameters should be dynamically adjusted during training and shows the potential for more insights on AutoRL problems that can be gained through landscape analyses.
Hyperparameter Optimization
Open-Ended Question Answering
+1
Towards Meta-learned Algorithm Selection using Implicit Fidelity Information
Most approaches for this problem rely on pre-computed dataset meta-features and landmarking performances to capture the salient topology of the datasets and those topologies that the algorithms attend to.
Contextualize Me -- The Case for Context in Reinforcement Learning
While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes.
