Picture for Changnan Xiao

Changnan Xiao

A Theory for Length Generalization in Learning to Reason

Add code
Mar 31, 2024
Figure 1 for A Theory for Length Generalization in Learning to Reason
Figure 2 for A Theory for Length Generalization in Learning to Reason
Figure 3 for A Theory for Length Generalization in Learning to Reason
Figure 4 for A Theory for Length Generalization in Learning to Reason
Viaarxiv icon

Conditions for Length Generalization in Learning Reasoning Skills

Add code
Dec 06, 2023
Viaarxiv icon

Learnability and Algorithm for Continual Learning

Add code
Jun 22, 2023
Figure 1 for Learnability and Algorithm for Continual Learning
Figure 2 for Learnability and Algorithm for Continual Learning
Figure 3 for Learnability and Algorithm for Continual Learning
Figure 4 for Learnability and Algorithm for Continual Learning
Viaarxiv icon

Open-World Continual Learning: Unifying Novelty Detection and Continual Learning

Add code
Apr 20, 2023
Figure 1 for Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
Figure 2 for Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
Figure 3 for Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
Figure 4 for Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
Viaarxiv icon

Mastering Strategy Card Game (Hearthstone) with Improved Techniques

Add code
Mar 09, 2023
Figure 1 for Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Figure 2 for Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Figure 3 for Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Figure 4 for Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Viaarxiv icon

Mastering Strategy Card Game via End-to-End Policy and Optimistic Smooth Fictitious Play

Add code
Mar 07, 2023
Figure 1 for Mastering Strategy Card Game  via End-to-End Policy and Optimistic Smooth Fictitious Play
Figure 2 for Mastering Strategy Card Game  via End-to-End Policy and Optimistic Smooth Fictitious Play
Figure 3 for Mastering Strategy Card Game  via End-to-End Policy and Optimistic Smooth Fictitious Play
Figure 4 for Mastering Strategy Card Game  via End-to-End Policy and Optimistic Smooth Fictitious Play
Viaarxiv icon

A Theoretical Study on Solving Continual Learning

Add code
Nov 04, 2022
Figure 1 for A Theoretical Study on Solving Continual Learning
Figure 2 for A Theoretical Study on Solving Continual Learning
Figure 3 for A Theoretical Study on Solving Continual Learning
Figure 4 for A Theoretical Study on Solving Continual Learning
Viaarxiv icon

Generalized Data Distribution Iteration

Add code
Jun 20, 2022
Figure 1 for Generalized Data Distribution Iteration
Figure 2 for Generalized Data Distribution Iteration
Figure 3 for Generalized Data Distribution Iteration
Figure 4 for Generalized Data Distribution Iteration
Viaarxiv icon

Continual Learning Based on OOD Detection and Task Masking

Add code
Mar 17, 2022
Figure 1 for Continual Learning Based on OOD Detection and Task Masking
Figure 2 for Continual Learning Based on OOD Detection and Task Masking
Figure 3 for Continual Learning Based on OOD Detection and Task Masking
Figure 4 for Continual Learning Based on OOD Detection and Task Masking
Viaarxiv icon

GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning

Add code
Jun 15, 2021
Figure 1 for GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Figure 2 for GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Figure 3 for GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Figure 4 for GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Viaarxiv icon