Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
MRTPO assigns each reward's advantage only to tokens relevant to that verifier, improving multi-reward RL.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #multi-reward
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.
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning
CorrGRPO normalizes multi-reward GRPO with Pearson correlations so large rewards do not drown smaller signals.