Score Centering Stabilizes Off-policy Reinforcement Learning
Paper attributes RL instability under training-inference mismatch to accumulating drift and introduces score centering, an additive correction that stabilizes training.
1 stories, newest first · one card per story
Paper attributes RL instability under training-inference mismatch to accumulating drift and introduces score centering, an additive correction that stabilizes training.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views