2 citations · 4 across the 12 of their papers we have counts for
8 papers · 1 filter
Time-Uniform Self-Normalized Concentration for Discounted Least Squares: Limits and Corrections
Yi-Shan Wu
Self-normalized concentration inequalities are standard tools in bandit and reinforcement-learning analyses. A widely used weighted extension claims an analogous time-uniform guara…
ObjectRL: An Object-Oriented Reinforcement Learning Codebase
Gulcin Baykal, Abdullah Akgül, Manuel Haussmann +4
ObjectRL is an open-source Python codebase for deep reinforcement learning (RL), designed for research-oriented prototyping with minimal programming effort. Unlike existing codebas…
Adaptive Ensemble Aggregation for Actor-Critics
Nicklas Werge, Yi-Shan Wu, Manuel Haussmann +2
Ensembles are ubiquitous in off-policy actor-critic learning, yet their efficacy depends critically on how they are aggregated. Current methods typically rely on static rules or ta…
Deep Actor-Critics with Tight Risk Certificates
Bahareh Tasdighi, Manuel Haussmann, Yi-Shan Wu +2
Deep actor-critic algorithms have reached a level where they influence everyday life. They are a driving force behind continual improvement of large language models through user fe…
Improving Actor-Critic Training with Steerable Action-Value Approximation Errors
Bahareh Tasdighi, Nicklas Werge, Yi-Shan Wu +1
Off-policy actor-critic algorithms have shown strong potential in deep reinforcement learning for continuous control tasks. Their success primarily comes from leveraging pessimisti…
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Yi-Shan Wu, Yijie Zhang, Badr-Eddine Chérief-Abdellatif +1
PAC-Bayesian analysis is a frequentist framework for incorporating prior knowledge into learning. It was inspired by Bayesian learning, which allows sequential data processing and…
Deep Exploration with PAC-Bayes
Bahareh Tasdighi, Manuel Haussmann, Nicklas Werge +2
Reinforcement learning (RL) for continuous control under delayed rewards is an under-explored problem despite its significance in real-world applications. Many complex skills are b…
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Yi-Shan Wu, Andrés R. Masegosa, Stephan S. Lorenzen +2
We present a new second-order oracle bound for the expected risk of a weighted majority vote. The bound is based on a novel parametric form of the Chebyshev- Cantelli inequality (a…