Vincent
  • Bio
  • Experience
  • Papers
  • Recent & Upcoming Talks
    • Example Talk
  • Projects
  • Publications
    • Switching the Loss Reduces the Cost in Batch Reinforcement Learning
    • Investigating the properties of neural network representations in reinforcement learning
    • When is Offline Policy Selection Feasible for Reinforcement Learning?
    • Exploiting action impact regularity and exogenous state variables for offline reinforcement learning
    • Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
    • Measuring and Mitigating Interference in Reinforcement Learning
    • No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
    • Training Recurrent Neural Networks Online by Learning Explicit State Variables
    • The utility of sparse representations for control in reinforcement learning
    • A Value Function Basis for Nexting and Multi-step Prediction
    • Incrementally Learning Functions of the Return
    • Attribute-aware recommender system based on collaborative filtering: Survey and classification
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python

Switching the Loss Reduces the Cost in Batch Reinforcement Learning

Jan 2, 2024·
Alex Ayoub
,
Kaiwen Wang
Vincent Liu
Vincent Liu
,
Samuel Robertson
,
James McInerney
,
Dawen Liang
,
Nathan Kallus
,
Csaba Szepesvári
· 0 min read
Cite URL
Type
Conference paper
Publication
International Conference on Machine Learning
Last updated on Jan 2, 2024
Vincent Liu
Authors
Vincent Liu
Postdoctoral Research and Teaching Fellow
Investigating the properties of neural network representations in reinforcement learning Jan 1, 2024 →

© 2024 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.