Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL
DARA reweights multi-reward RL by reward density, reaching compliance faster than GDPO on tools and math.
1 stories, newest first · one card per story
DARA reweights multi-reward RL by reward density, reaching compliance faster than GDPO on tools and math.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views