Picture for Jean Vassoyan

Jean Vassoyan

CB

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

Add code
Feb 10, 2025
Figure 1 for Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Figure 2 for Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Figure 3 for Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Figure 4 for Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
Viaarxiv icon

A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents

Add code
Nov 18, 2024
Figure 1 for A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents
Figure 2 for A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents
Figure 3 for A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents
Figure 4 for A Pre-Trained Graph-Based Model for Adaptive Sequencing of Educational Documents
Viaarxiv icon

Towards Scalable Adaptive Learning with Graph Neural Networks and Reinforcement Learning

Add code
May 10, 2023
Viaarxiv icon