Picture for Qingyuan Wu

Qingyuan Wu

Model-Based Reward Shaping for Adversarial Inverse Reinforcement Learning in Stochastic Environments

Add code
Oct 04, 2024
Viaarxiv icon

Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning

Add code
Jun 12, 2024
Viaarxiv icon

Highway Value Iteration Networks

Add code
Jun 05, 2024
Viaarxiv icon

Highway Reinforcement Learning

Add code
May 28, 2024
Viaarxiv icon

Variational Delayed Policy Optimization

Add code
May 23, 2024
Viaarxiv icon

Boosting Long-Delayed Reinforcement Learning with Auxiliary Short-Delayed Task

Add code
Feb 05, 2024
Viaarxiv icon

State-wise Safe Reinforcement Learning With Pixel Observations

Add code
Nov 03, 2023
Viaarxiv icon

Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts

Add code
Apr 11, 2022
Figure 1 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 2 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 3 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Figure 4 for Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts
Viaarxiv icon