Tim Brys
YOU?
Author Swipe
View article: Improving Convergence of CMA-ES Through Structure-Driven Discrete Recombination
Improving Convergence of CMA-ES Through Structure-Driven Discrete Recombination Open
Evolutionary Strategies (ES) are a class of continuous optimization algorithms that have proven to perform very well on hard optimization problems. Whereas in earlier literature, both intermediate and discrete recombination operators were …
View article: Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Directed Policy Gradient for Safe Reinforcement Learning with Human Advice Open
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and…
View article: Directed Policy Gradient for Safe Reinforcement Learning with Human\n Advice
Directed Policy Gradient for Safe Reinforcement Learning with Human\n Advice Open
Many currently deployed Reinforcement Learning agents work in an environment\nshared with humans, be them co-workers, users or clients. It is desirable that\nthese agents adjust to people's preferences, learn faster thanks to their help,\n…
View article: Adapting to Concept Drift in Credit Card Transaction Data Streams Using Contextual Bandits and Decision Trees
Adapting to Concept Drift in Credit Card Transaction Data Streams Using Contextual Bandits and Decision Trees Open
Credit card transactions predicted to be fraudulent by automated detection systems are typically handed over to human experts for verification. To limit costs, it is standard practice to select only the most suspicious transactions for inv…
View article: Multi-objectivization and ensembles of shapings in reinforcement learning
Multi-objectivization and ensembles of shapings in reinforcement learning Open
View article: Preface to the special issue: adaptive and learning agents
Preface to the special issue: adaptive and learning agents Open
An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.
View article: Using PCA to Efficiently Represent State Spaces
Using PCA to Efficiently Represent State Spaces Open
Reinforcement learning algorithms need to deal with the exponential growth of states and actions when exploring optimal control in high-dimensional spaces. This is known as the curse of dimensionality. By projecting the agent's state onto …
View article: Off-Policy Reward Shaping with Ensembles
Off-Policy Reward Shaping with Ensembles Open
Potential-based reward shaping (PBRS) is an effective and popular technique to speed up reinforcement learning by leveraging domain knowledge. While PBRS is proven to always preserve optimal policies, its effect on learning speed is determ…