Accelerating RL for LLM Reasoning with Optimal Advantage Regression
Paper
•
2505.20686
•
Published
•
2
Accelerating RL for LLM Reasoning with Optimal Advantage Reg
-
-
Cornell-AGI/gsm8k_size_qwen2.5_1.5b_eval
Viewer • Updated • 7.47k • 79 -
Cornell-AGI/gsm8k_size_qwen2.5_3b_eval
Viewer • Updated • 7.47k • 81 -
Cornell-AGI/gsm8k_size_qwen2.5_7b_eval
Viewer • Updated • 7.47k • 81 -
Cornell-AGI/math_size_qwen2.5_1.5b_eval
Viewer • Updated • 7.5k • 84 -
Cornell-AGI/math_size_qwen2.5_3b_eval
Viewer • Updated • 7.5k • 80 -
Cornell-AGI/math_size_qwen2.5_7b_eval
Viewer • Updated • 7.5k • 79 -
Cornell-AGI/apo_math_qwen2.5_1.5b
Text Generation • Updated • 8 -
Cornell-AGI/apo_math_qwen2.5_3b
Text Generation • Updated • 5 -
Cornell-AGI/apo_math_qwen2.5_7b
Text Generation • Updated • 9 • 1 -
Cornell-AGI/ppo_math_qwen2.5_1.5b
Text Generation • Updated • 5 -
Cornell-AGI/ppo_math_qwen2.5_3b
Text Generation • Updated • 5 -
Cornell-AGI/ppo_math_qwen2.5_7b
Text Generation • Updated • 5 -
Cornell-AGI/grpo_math_qwen2.5_1.5b
Text Generation • Updated • 7 -
Cornell-AGI/grpo_math_qwen2.5_3b
Text Generation • Updated • 5 -
Cornell-AGI/grpo_math_qwen2.5_7b
Text Generation • Updated • 5 -
Cornell-AGI/rebel_math_qwen2.5_1.5b
Text Generation • Updated • 16 -
Cornell-AGI/rebel_math_qwen2.5_3b
Text Generation • Updated • 5 -
Cornell-AGI/rebel_math_qwen2.5_7b
Text Generation • Updated • 5