Picture for Vincent Liu

Vincent Liu

Carbon Connect: An Ecosystem for Sustainable Computing

May 22, 2024
Viaarxiv icon

Switching the Loss Reduces the Cost in Batch Reinforcement Learning

Mar 12, 2024
Figure 1 for Switching the Loss Reduces the Cost in Batch Reinforcement Learning
Figure 2 for Switching the Loss Reduces the Cost in Batch Reinforcement Learning
Figure 3 for Switching the Loss Reduces the Cost in Batch Reinforcement Learning
Viaarxiv icon

Under the Surface: Tracking the Artifactuality of LLM-Generated Data

Add code
Jan 30, 2024
Viaarxiv icon

When is Offline Policy Selection Sample Efficient for Reinforcement Learning?

Add code
Dec 04, 2023
Viaarxiv icon

Measuring and Mitigating Interference in Reinforcement Learning

Jul 10, 2023
Figure 1 for Measuring and Mitigating Interference in Reinforcement Learning
Figure 2 for Measuring and Mitigating Interference in Reinforcement Learning
Figure 3 for Measuring and Mitigating Interference in Reinforcement Learning
Figure 4 for Measuring and Mitigating Interference in Reinforcement Learning
Viaarxiv icon

Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments

Feb 23, 2023
Figure 1 for Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Figure 2 for Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Figure 3 for Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Figure 4 for Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Viaarxiv icon

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving

Add code
Feb 22, 2023
Figure 1 for AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Figure 2 for AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Figure 3 for AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Figure 4 for AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Viaarxiv icon

No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

Add code
May 18, 2022
Figure 1 for No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
Figure 2 for No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
Figure 3 for No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
Figure 4 for No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
Viaarxiv icon

Investigating the Properties of Neural Network Representations in Reinforcement Learning

Mar 30, 2022
Figure 1 for Investigating the Properties of Neural Network Representations in Reinforcement Learning
Figure 2 for Investigating the Properties of Neural Network Representations in Reinforcement Learning
Figure 3 for Investigating the Properties of Neural Network Representations in Reinforcement Learning
Figure 4 for Investigating the Properties of Neural Network Representations in Reinforcement Learning
Viaarxiv icon

DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning

Add code
Nov 23, 2021
Figure 1 for DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning
Figure 2 for DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning
Figure 3 for DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning
Figure 4 for DABS: A Domain-Agnostic Benchmark for Self-Supervised Learning
Viaarxiv icon