18.
Cyclical Entropy Eruption in agent RL
Agent RL training can enter recurring entropy eruptions that make it far less stable than reasoning-only RL
@SharonYixuanLi on Backlist
1 appearance on the backlist front page in the last 30 days.
1 appearance on the backlist front page in the last 30 days.
Agent RL training can enter recurring entropy eruptions that make it far less stable than reasoning-only RL